© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211776
    Prev
    Next
    INDEX
    Explanations

    student discussions and answers

    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_5_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
    OFF
    0.83
     indiquer
    0.82
    '
    0.79
    LIKE
    0.79
     لأ
    0.78
    ра
    0.76
    К
    0.75
    st
    0.75
    ON
    0.75
    d
    0.74
    POSITIVE LOGITS
    in
    1.08
     a
    0.93
    ید
    0.89
    ین
    0.89
     you
    0.87
     playful
    0.85
    </h2>
    0.82
     music
    0.82
     wine
    0.80
    of
    0.80
    Activations Density 0.010%

    No Known Activations