© 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. 46604
    Prev
    Next
    INDEX
    Explanations

    Battlefield, Batcave, Batgirl, batting average, Goddess

    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
    ),
    0.89
    RI
    0.85
    I
    0.80
    on
    0.80
    as
    0.78
    LE
    0.77
    DEN
    0.75
    ).
    0.75
    i
    0.74
    ST
    0.72
    POSITIVE LOGITS
    л
    0.81
    이나
    0.74
    ר
    0.73
    티브
    0.72
    ى
    0.72
    м
    0.71
    ه
    0.71
    к
    0.70
    нику
    0.70
    ח
    0.67
    Activations Density 0.002%

    No Known Activations