© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206005
    Prev
    Next
    INDEX
    Explanations

    list of words

    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_37_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
     একদিকে
    0.38
    一方面
    0.37
    パス
    0.36
     ابتدا
    0.35
    mittent
    0.35
    ارڈ
    0.35
    ില്ല
    0.34
    𝑵
    0.34
    引领
    0.34
    (()
    0.34
    POSITIVE LOGITS
     Be
    0.37
     actually
    0.37
    ボル
    0.37
    தமிழ
    0.37
     Abit
    0.36
     att
    0.35
    FZ
    0.35
     Au
    0.35
     finer
    0.35
     Hanover
    0.35
    Activations Density 0.175%

    No Known Activations