© 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. 3640
    Prev
    Next
    INDEX
    Explanations

    a mix of programming code, chemical formulas, and statistical analysis of the results of things like medical trials.

    oai_token-act-pair · gemini-2.0-flash

    Begins with "Co"

    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
     McGee
    -0.63
    mce
    -0.62
    MCI
    -0.62
    xFC
    -0.60
    ECI
    -0.60
     sc
    -0.59
    fcc
    -0.59
     RC
    -0.59
    aci
    -0.58
     IC
    -0.58
    POSITIVE LOGITS
     CO
    0.82
     Co
    0.79
     c
    0.77
     CQ
    0.77
     C
    0.75
     COT
    0.74
    CO
    0.69
    Co
    0.68
     Coss
    0.68
     Coh
    0.67
    Activations Density 2.255%

    No Known Activations