© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4178
    Prev
    Next
    INDEX
    Explanations

    blocks of code or configuration that define commands, groups, and tasks

    oai_token-act-pair · gemini-2.0-flash

    programming commands or parameters

    np_token-act-pair-logits · gpt-4o-mini

    Source code/tests

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    UserScript
    -0.43
     Fin
    -0.42
     puntas
    -0.42
     Dink
    -0.41
    addPreferredGap
    -0.41
     prosecution
    -0.40
     Sélectionnez
    -0.39
    IsContent
    -0.38
     inspection
    -0.38
    Fin
    -0.37
    POSITIVE LOGITS
    InitVars
    0.79
    Datuak
    0.79
     unknownFields
    0.76
     /\.(
    0.69
    basicConfig
    0.68
     TextAppearance
    0.63
     NSCoder
    0.62
    oredCriteria
    0.62
     disambiguazione
    0.60
    #+#
    0.60
    Activations Density 2.296%

    No Known Activations