© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11420
    Prev
    Next
    INDEX
    Explanations

    words with the "descri", "opho", "cor" or "adsrob", and "pertur" prefixes/beginnings.

    oai_token-act-pair · gemini-2.0-flash

    b

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ::::::::
    -0.47
    antMatchers
    -0.43
    ersdorf
    -0.39
    Điều
    -0.39
    MultipartFile
    -0.37
    addComponent
    -0.35
    IntoConstraints
    -0.35
     "..\..\..\
    -0.34
    μφ
    -0.34
     CEP
    -0.33
    POSITIVE LOGITS
    b
    1.00
    ｂ
    0.93
     b
    0.92
    bt
    0.89
    bu
    0.88
    bex
    0.86
    բ
    0.84
    bs
    0.84
    bf
    0.84
    bd
    0.83
    Activations Density 0.592%

    No Known Activations