© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11826
    Prev
    Next
    INDEX
    Explanations

    mentions of programs, projects, or successes with some weak negative sentiment for some reason.

    oai_token-act-pair · gemini-2.0-flash

    success

    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
     success
    -3.23
     Success
    -2.94
    success
    -2.70
    Success
    -2.67
     SUCCESS
    -2.48
     éxito
    -2.38
     succès
    -2.33
     succeed
    -2.27
     sucesso
    -2.20
     successful
    -2.17
    POSITIVE LOGITS
     Архиви
    0.52
     Vikipedi
    0.47
     chère
    0.46
    ỳ
    0.46
    fes
    0.44
    */,
    0.44
    RTCF
    0.43
    kmäler
    0.43
     виправивши
    0.43
     */,
    0.42
    Activations Density 2.237%

    No Known Activations