© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4660
    Prev
    Next
    INDEX
    Explanations

    numerical values or identifiers, especially those with unusual formatting, potentially representing configurations, statistics or some kind of code.

    oai_token-act-pair · gemini-2.0-flash

    code and calculations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     AND
    -0.47
     *_
    -0.41
     OR
    -0.40
     BUT
    -0.40
    -0.39
    lor
    -0.38
     q
    -0.37
     **
    -0.37
    */
    -0.35
     die
    -0.35
    POSITIVE LOGITS
     negroes
    0.93
     Shakspeare
    0.91
     nephe
    0.89
     steamboat
    0.88
     Efq
    0.86
     oars
    0.86
     caldera
    0.86
     masts
    0.84
     camels
    0.83
     rhod
    0.83
    Activations Density 19.594%
    No Known Activations