© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3323
    Prev
    Next
    INDEX
    Explanations

    technical language related to a variety of fields, including gaming, automotive engineering, and legal proceedings.

    oai_token-act-pair · gemini-2.0-flash

    gerunds or present participles

    np_token-act-pair-logits · gpt-4o-mini

    -ing verbs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cruzado
    -0.43
    Дереккөздер
    -0.42
    TableHead
    -0.41
    WriteLiteral
    -0.40
     sağlar
    -0.40
     solas
    -0.40
    UnusedPrivate
    -0.39
     erle
    -0.39
     señ
    -0.38
     CanadaChoose
    -0.37
    POSITIVE LOGITS
     saying
    0.98
     offering
    0.96
     allowing
    0.95
     preferring
    0.94
     giving
    0.94
     choosing
    0.93
     claiming
    0.93
     providing
    0.93
     announcing
    0.92
     attempting
    0.92
    Activations Density 11.211%

    No Known Activations