© 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. 126178
    Prev
    Next
    INDEX
    Explanations

    Whisperwind locations

    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
     to
    0.74
    یس
    0.70
    )
    0.69
    ä
    0.68
     It
    0.65
    )。
    0.65
    Repositories
    0.65
    </strong>
    0.64
    </h3>
    0.63
    ید
    0.62
    POSITIVE LOGITS
    мени
    0.59
    e
    0.59
    getNum
    0.55
    s
    0.55
    uridad
    0.53
     deplorable
    0.52
    t
    0.50
     compute
    0.50
     computationally
    0.49
    an
    0.49
    Activations Density 0.001%

    No Known Activations