© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4085
    Prev
    Next
    INDEX
    Explanations

    code related to UI implementation

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     A
    -0.75
     bar
    -0.72
     van
    -0.72
    __(/*!
    -0.71
     raz
    -0.71
     del
    -0.67
     im
    -0.66
     The
    -0.66
     to
    -0.66
     a
    -0.66
    POSITIVE LOGITS
     Anſ
    1.05
     Reſ
    1.02
     myſelf
    0.96
     Monfieur
    0.96
     Diſ
    0.96
     Houſe
    0.96
     Chriftian
    0.95
     Eſ
    0.95
     Perſ
    0.92
     Conſ
    0.91
    Activations Density 1.426%

    No Known Activations