© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9379
    Prev
    Next
    INDEX
    Explanations

    action verbs and nouns, especially when they are associated with change.

    oai_token-act-pair · gemini-2.0-flash

    question and answer pairs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    tvguidetime
    -0.81
    rawDesc
    -0.80
    PAIGN
    -0.72
    PhysRevLett
    -0.72
    :✨
    -0.71
    NUMX
    -0.70
    WriteAttribute
    -0.68
     incomplète
    -0.66
     hemsida
    -0.65
    tagHelperRunner
    -0.65
    POSITIVE LOGITS
    add
    0.43
     estekak
    0.42
    ss
    0.41
    liz
    0.40
    Ned
    0.38
    <unused63>
    0.38
    AL
    0.38
     Horizons
    0.37
    all
    0.37
    ind
    0.37
    Activations Density 5.385%

    No Known Activations