© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14862
    Prev
    Next
    INDEX
    Explanations

    database lock update

    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_13_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
    koz
    0.47
     RPG
    0.44
     propag
    0.44
    tj
    0.43
    /
    0.43
     daftar
    0.43
    uhan
    0.42
     Notebook
    0.42
    tor
    0.42
    kal
    0.42
    POSITIVE LOGITS
    ineries
    0.53
     وسط
    0.49
     kesk
    0.48
     ܒ
    0.46
     באמצע
    0.45
     ஏழு
    0.43
     kraja
    0.43
    acağı
    0.42
     початку
    0.42
    坩
    0.41
    Activations Density 0.007%

    No Known Activations