© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3693
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly Javascript, using '.' and '=', and single quotes

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    #+#
    -0.65
    AsUp
    -0.52
    Становништво
    -0.51
    ponses
    -0.51
    onViewCreated
    -0.49
    InputBorder
    -0.49
     PagesJaunes
    -0.47
    stdc
    -0.47
    wußt
    -0.46
    cences
    -0.45
    POSITIVE LOGITS
    Geplaatst
    0.65
    EndContext
    0.65
    ArgumentParser
    0.63
     }</
    0.61
    awaiter
    0.60
     незавершена
    0.59
    GraphicsUnit
    0.58
    ]))
    0.54
    enterOuterAlt
    0.53
    interopRequire
    0.52
    Activations Density 5.575%

    No Known Activations