© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9766
    Prev
    Next
    INDEX
    Explanations

    specific formatting prefixes, such as numbers followed by colons, bracketed numbers, line numbers, and the "Aim #"

    oai_token-act-pair · gemini-2.0-flash

    code references and comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    yntaxException
    -0.68
    HostException
    -0.65
     تضيفلها
    -0.64
    URLException
    -0.62
    MethodManager
    -0.61
     tslint
    -0.60
    GeneratedCode
    -0.59
    HasColumnType
    -0.59
     neutre
    -0.58
     ErrIntOverflow
    -0.57
    POSITIVE LOGITS
    beiten
    0.43
    DOCT
    0.42
     resourceCulture
    0.42
    первых
    0.42
    sify
    0.42
    twimg
    0.42
    oxo
    0.40
     Und
    0.39
    riel
    0.39
    addPreferredGap
    0.39
    Activations Density 3.542%

    No Known Activations