© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10541
    Prev
    Next
    INDEX
    Explanations

    sentences expressing a plan or an intention involving "we" or "you."

    oai_token-act-pair · gemini-2.0-flash

    unrelated technical terms and tags

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

    you/we/I

    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
     Untersch
    -0.47
    ote
    -0.44
    scen
    -0.43
     soñar
    -0.42
    yez
    -0.42
    TRA
    -0.41
    шай
    -0.40
    sprüng
    -0.40
     refusé
    -0.40
     yourself
    -0.40
    POSITIVE LOGITS
     nahilalakip
    0.93
     صوتيه
    0.83
    AddTagHelper
    0.83
    хьтан
    0.80
     يتيمه
    0.80
    MigrationBuilder
    0.79
    bootstrapcdn
    0.79
    principalTable
    0.79
     CreateTagHelper
    0.78
     виправивши
    0.78
    Activations Density 1.653%

    No Known Activations