© 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. 3077
    Prev
    Next
    INDEX
    Explanations

    places someone is stating information while refraining from providing specific details

    oai_token-act-pair · gemini-2.0-flash

    Specifying or clarifying details

    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
    TypedDataSet
    -0.59
    featureID
    -0.59
    keyColumn
    -0.53
     muri
    -0.53
    AutoScale
    -0.52
     متعلقه
    -0.51
     demurrer
    -0.51
     trajets
    -0.50
    +#+
    -0.50
    testcase
    -0.50
    POSITIVE LOGITS
     détail
    0.91
     details
    0.91
     disclosing
    0.87
     specify
    0.86
     clarify
    0.86
     précisé
    0.85
     disclose
    0.85
    details
    0.83
     explain
    0.83
     detail
    0.82
    Activations Density 1.895%

    No Known Activations