© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252573
    Prev
    Next
    INDEX
    Explanations

    parts of words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    endl
    0.41
     amour
    0.40
     End
    0.40
     엔
    0.40
     रत्न
    0.39
     END
    0.39
     끝
    0.38
     affirmations
    0.38
    끝
    0.37
    End
    0.37
    POSITIVE LOGITS
    ahan
    0.43
    und
    0.42
    ån
    0.40
    ULL
    0.39
    BorderSize
    0.39
     Gesch
    0.38
    indra
    0.38
     Анато
    0.37
    undo
    0.36
    UND
    0.36
    Activations Density 0.000%

    No Known Activations