© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45500
    Prev
    Next
    INDEX
    Explanations

    plastic wrap or film

    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_10_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
    an
    0.95
    el
    0.79
    on
    0.74
    es
    0.71
    en
    0.70
    a
    0.65
    s
    0.63
    ه
    0.63
    z
    0.62
     $
    0.59
    POSITIVE LOGITS
    ।
    0.70
    ।’
    0.63
    ОВ
    0.63
    ។
    0.63
    ।"
    0.62
    Cré
    0.60
    被
    0.60
    。”
    0.59
    ONT
    0.59
    ”।
    0.59
    Activations Density 0.015%

    No Known Activations