© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122098
    Prev
    Next
    INDEX
    Explanations

    rolled up

    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_3_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
     uncanny
    0.64
    ﺍ
    0.64
    \
    0.61
    ために
    0.59
     υψη
    0.57
    #
    0.56
    And
    0.55
     অত্যা
    0.55
     stric
    0.55
    BlockHash
    0.54
    POSITIVE LOGITS
    ↵
    0.80
    นะ
    0.72
    aa
    0.72
    ang
    0.71
    ↵↵
    0.69
    IL
    0.67
    ید
    0.66
    t
    0.64
    UL
    0.63
    ಿಂದ
    0.62
    Activations Density 0.000%

    No Known Activations