© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10690
    Prev
    Next
    INDEX
    Explanations

    technical texts and jargon.

    oai_token-act-pair · gemini-2.0-flash

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    []
    -0.70
    ^(@)
    -0.69
     Offisielt
    -0.68
    ThroughAttribute
    -0.63
    lesi
    -0.60
    arques
    -0.60
    veu
    -0.60
     Audiodateien
    -0.60
    delli
    -0.57
    >>()
    -0.57
    POSITIVE LOGITS
     الدولى
    0.66
    AutoScaleMode
    0.60
    RTEX
    0.59
    AppMethodBeat
    0.52
    bä
    0.50
    featureID
    0.47
    hoeddwyd
    0.47
     Walkover
    0.46
     disambiguazione
    0.44
    DebuggerNonUser
    0.44
    Activations Density 3.347%

    No Known Activations