© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38899
    Prev
    Next
    INDEX
    Explanations

    Silent Hill, living, Panda, Cats

    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_3_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
    м
    0.68
    ل
    0.63
    うまく
    0.58
     reorgan
    0.57
    했
    0.57
    /
    0.57
    ל
    0.57
     embodiments
    0.56
     renormal
    0.55
    দের
    0.54
    POSITIVE LOGITS
    MC
    0.72
    to
    0.70
    n
    0.70
    ai
    0.69
     Meesho
    0.64
    iv
    0.63
    CS
    0.63
    ox
    0.61
    ats
    0.60
    CA
    0.60
    Activations Density 0.014%

    No Known Activations