© 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. 10666
    Prev
    Next
    INDEX
    Explanations

    words relating to architecture and geometry

    oai_token-act-pair · gemini-2.0-flash

    planning/projection

    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
    berus
    -0.49
     gap
    -0.47
     steg
    -0.47
    illip
    -0.47
     token
    -0.46
    kommer
    -0.42
    posite
    -0.42
    genstein
    -0.41
    posti
    -0.41
    ில
    -0.40
    POSITIVE LOGITS
     ModelExpression
    1.11
     ſche
    1.00
     plan
    0.94
     plans
    0.94
    plans
    0.91
     planen
    0.91
    <bos>
    0.91
    Plans
    0.90
     Plans
    0.89
     planning
    0.88
    Activations Density 1.352%

    No Known Activations