© 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. 9125
    Prev
    Next
    INDEX
    Explanations

    mentions of public transportation and locations

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with 'P' or 'H'

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

    Public transit

    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
     Monfieur
    -1.08
     pleaſure
    -1.04
     Efq
    -1.04
     itſelf
    -1.02
     Jefus
    -1.02
     raiſ
    -1.02
     Theſe
    -0.99
     myſelf
    -0.98
     ſeveral
    -0.97
     Shakspeare
    -0.97
    POSITIVE LOGITS
     I
    0.57
     P
    0.57
     em
    0.52
     H
    0.52
    ,
    0.51
     -
    0.51
     (
    0.50
     [
    0.49
     T
    0.49
    P
    0.47
    Activations Density 0.725%

    No Known Activations