© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39551
    Prev
    Next
    INDEX
    Explanations

    ple

    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_11_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
     دارو
    0.61
    獺
    0.60
    سی
    0.59
    ک
    0.59
    کات
    0.58
    Sebagai
    0.58
    💕
    0.58
    ഽ
    0.57
    🦦
    0.57
     سنوات
    0.57
    POSITIVE LOGITS
    em
    0.66
    en
    0.66
    ig
    0.63
    verting
    0.59
    ag
    0.58
    ed
    0.58
    es
    0.57
    t
    0.57
    ards
    0.56
     (
    0.55
    Activations Density 0.000%

    No Known Activations