© 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. 12688
    Prev
    Next
    INDEX
    Explanations

    symbols, equations, and references like figures in scientific texts.

    oai_token-act-pair · gemini-2.0-flash

    (

    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
     (
    -1.38
    ,
    -1.20
    (
    -1.19
    .
    -1.05
    -
    -1.04
    ↵
    -0.87
     et
    -0.84
     P
    -0.80
     B
    -0.79
     J
    -0.79
    POSITIVE LOGITS
     itſelf
    2.06
     myſelf
    1.86
     pleaſure
    1.77
     Monfieur
    1.73
    ſelf
    1.69
     Diſ
    1.67
     Reſ
    1.66
     raiſ
    1.65
     Majefty
    1.64
     purpoſe
    1.63
    Activations Density 13.358%

    No Known Activations