© 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. 11073
    Prev
    Next
    INDEX
    Explanations

    a mix of names, headings, log file snippets, and code snippets.

    oai_token-act-pair · gemini-2.0-flash

    technical documents

    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
     كومونز
    -0.77
    orini
    -0.55
    schild
    -0.54
    енча
    -0.54
    moveToFirst
    -0.53
    ])->
    -0.52
    '):
    -0.52
    bibinfo
    -0.52
    はじめに
    -0.52
     PHASE
    -0.51
    POSITIVE LOGITS
     NSCoder
    0.65
     Wikimedijinoj
    0.56
    MigrationBuilder
    0.53
    发表于
    0.51
    IUrlHelper
    0.48
    CopyWith
    0.47
    InstrumentedTest
    0.47
    AlterField
    0.45
    gouv
    0.45
     utafiti
    0.45
    Activations Density 3.798%

    No Known Activations