© 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-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130437
    Prev
    Next
    INDEX
    Explanations

    Scalability, Gallai theorem, Bosons

    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_1_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
    ية
    1.43
     on
    1.30
    Д
    1.30
    很
    1.30
    ם
    1.20
     игро
    1.16
    ي
    1.13
     ruim
    1.07
    }
    1.07
     beneficios
    1.05
    POSITIVE LOGITS
    ar
    1.44
    the
    1.42
    is
    1.41
    h
    1.38
    er
    1.24
    in
    1.23
    den
    1.22
    em
    1.19
    t
    1.17
    r
    1.15
    Activations Density 0.000%

    No Known Activations