© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198387
    Prev
    Next
    INDEX
    Explanations

    synthesizer, posts, string, Dynasty

    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_4_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
    ר
    1.14
    ث
    1.12
    ر
    1.04
    ک
    1.04
    r
    1.03
    то
    1.02
    ता
    0.97
    та
    0.96
    A
    0.95
    and
    0.92
    POSITIVE LOGITS
    .
    1.00
    -
    0.89
     moan
    0.88
                          
    0.87
     nắng
    0.87
     falsa
    0.84
     изготов
    0.80
     verwend
    0.79
     manter
    0.79
     mecánica
    0.79
    Activations Density 0.000%

    No Known Activations