© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10233
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially those containing dollar signs, image references, and tree structures

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    Пото
    -0.52
    曖昧さ回避
    -0.49
    ISODE
    -0.49
    <bos>
    -0.46
    PyExc
    -0.45
    diale
    -0.45
     @"
    -0.44
    FieldNumber
    -0.43
     neutr
    -0.42
    fusc
    -0.42
    POSITIVE LOGITS
    ConstraintMaker
    0.83
    ollectionView
    0.73
     profonde
    0.70
    tagext
    0.69
     getopt
    0.66
    BeginContext
    0.63
     profundos
    0.62
     Tiefen
    0.62
     profondeur
    0.60
    OrNil
    0.60
    Activations Density 1.594%

    No Known Activations