© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200342
    Prev
    Next
    INDEX
    Explanations

    weight distribution, foundation, speed, weak

    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_12_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
    </h2>
    0.51
    Are
    0.50
     are
    0.48
    eflow
    0.44
    </h3>
    0.41
    s
    0.41
    amsmath
    0.41
    Этот
    0.40
    П
    0.40
    В
    0.40
    POSITIVE LOGITS
     Highlands
    0.46
     கொள்க
    0.42
    帏
    0.42
     millilit
    0.41
    RationalValue
    0.41
     highlands
    0.41
     tailles
    0.41
    匣
    0.41
     highland
    0.40
     لیں
    0.40
    Activations Density 0.002%

    No Known Activations