© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 65448
    Prev
    Next
    INDEX
    Explanations

    import BeautifulSoup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_41_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chicken
    0.42
    chicken
    0.41
     ऋषभ
    0.38
    chromo
    0.38
     Pensions
    0.38
     স্বীকৃত
    0.38
     tulang
    0.37
    닭
    0.37
     चिकन
    0.36
     colectivo
    0.36
    POSITIVE LOGITS
     locks
    0.42
    uwe
    0.40
    Dead
    0.39
    Lewis
    0.39
    ձ
    0.39
    ജ
    0.39
     stop
    0.39
     bunches
    0.39
    េស
    0.38
     bunch
    0.38
    Activations Density 0.000%

    No Known Activations