© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15288
    Prev
    Next
    INDEX
    Explanations

    words related to the regulations, safety and efficacy of products

    oai_token-act-pair · gemini-2.0-flash

    safety

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     pleaſure
    -0.63
     ſeveral
    -0.63
     Efq
    -0.60
     autorytatywna
    -0.60
     étoient
    -0.58
     cavitation
    -0.56
     themſelves
    -0.56
     Monfieur
    -0.56
     myſelf
    -0.56
     juſt
    -0.55
    POSITIVE LOGITS
    BeginContext
    0.66
     متعلقه
    0.63
    ThroughAttribute
    0.51
    ProgressHUD
    0.48
    endpush
    0.46
    ScopeManager
    0.46
    ⓧ
    0.44
    󠁢
    0.43
     se
    0.43
    hoga
    0.43
    Activations Density 3.209%

    No Known Activations