© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9453
    Prev
    Next
    INDEX
    Explanations

    the word "reply" or its variants.

    oai_token-act-pair · gemini-2.0-flash

    reply

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     AssemblyCompany
    -0.85
    neſs
    -0.77
     Houſe
    -0.74
     Anſ
    -0.73
    FundMe
    -0.71
     Majefty
    -0.71
    +#+#
    -0.70
     Forumite
    -0.69
     Efq
    -0.68
     ARXIV
    -0.68
    POSITIVE LOGITS
     Gennaio
    0.63
     generali
    0.62
    ScopeManager
    0.57
    en
    0.56
     another
    0.54
    SqlClient
    0.54
     Rabbits
    0.54
    er
    0.53
     anlay
    0.53
    RuleContext
    0.52
    Activations Density 0.695%

    No Known Activations