© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16030
    Prev
    Next
    INDEX
    Explanations

    occurrences of documents, motions, suits, or requests of information being stated

    oai_token-act-pair · gemini-2.0-flash

    states

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    tagHelperRunner
    -0.77
    hoeddwyd
    -0.71
    +#+#
    -0.70
     SafeMath
    -0.69
     дописавши
    -0.66
    Personensuche
    -0.66
     Meksiku
    -0.65
     EconPapers
    -0.64
    SharedCtor
    -0.62
    MigrationBuilder
    -0.60
    POSITIVE LOGITS
    πως
    0.48
    olese
    0.41
     plural
    0.40
    indelijk
    0.39
    weber
    0.39
    substack
    0.37
    noopener
    0.37
    Sébastien
    0.37
    bigcap
    0.36
     Dever
    0.36
    Activations Density 3.453%

    No Known Activations