© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34476
    Prev
    Next
    INDEX
    Explanations

    logistic Apache gradient

    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_31_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
     apprehended
    0.14
     sermon
    0.13
     prést
    0.12
    ermek
    0.12
     poderoso
    0.12
    AppDesigner
    0.12
    耸
    0.12
     meios
    0.11
     aperta
    0.11
     ferv
    0.11
    POSITIVE LOGITS
    Sync
    0.11
     Meyers
    0.11
     Lear
    0.10
     गुणन
    0.10
     Sync
    0.10
    ྙ
    0.10
     Chun
    0.10
    (-\
    0.10
     Hof
    0.10
     sync
    0.10
    Activations Density 0.000%

    No Known Activations