© 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. 13842
    Prev
    Next
    INDEX
    Explanations

    intensifiers, comparatives, and words indicating a large degree of change.

    oai_token-act-pair · gemini-2.0-flash

    adverbs describing change/comparison

    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
    __*/
    -0.56
    umi
    -0.46
    ("$.
    -0.45
    titura
    -0.43
    tempor
    -0.41
     aceptas
    -0.41
     mõ
    -0.40
    hofer
    -0.40
     Spri
    -0.40
    pkins
    -0.40
    POSITIVE LOGITS
     propOrder
    0.85
     للمعارف
    0.83
    ValueStyle
    0.72
    setVerticalGroup
    0.71
    inSlope
    0.71
    دانشنامهٔ
    0.69
    resave
    0.65
    ########.
    0.63
     Taktlose
    0.62
     calldata
    0.60
    Activations Density 0.685%

    No Known Activations