© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194534
    Prev
    Next
    INDEX
    Explanations

    react native StyleSheet import

    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_15_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
    ９
    0.62
    ッケージ
    0.55
    クラ
    0.54
    ５
    0.54
    qPCR
    0.53
    铐
    0.53
     Lack
    0.52
    缺点
    0.52
     TreeSet
    0.51
    ㄻ
    0.51
    POSITIVE LOGITS
     hasn
    0.52
     haven
    0.49
     contend
    0.49
     fakat
    0.49
    Thing
    0.47
     άλλα
    0.47
     hadn
    0.46
    Y
    0.46
     farther
    0.45
    Native
    0.44
    Activations Density 0.000%

    No Known Activations