© 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. 8719
    Prev
    Next
    INDEX
    Explanations

    proper names and dates

    oai_token-act-pair · gemini-2.0-flash

    Slovak names or phrases

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

    identifiers and versions

    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
     myſelf
    -1.72
     Monfieur
    -1.71
     itſelf
    -1.70
     Efq
    -1.67
     purpoſe
    -1.66
     ſtate
    -1.64
     Majefty
    -1.63
     Reſ
    -1.63
     pleaſure
    -1.56
     Diſ
    -1.55
    POSITIVE LOGITS
     và
    0.54
     ki
    0.54
     có
    0.51
     r
    0.50
     l
    0.47
     C
    0.46
     v
    0.45
     g
    0.45
     tan
    0.44
     di
    0.44
    Activations Density 2.935%

    No Known Activations