© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 201105
    Prev
    Next
    INDEX
    Explanations

    safetensors and tensors

    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_12_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
     millions
    0.50
     शकतात
    0.50
     살
    0.50
    յան
    0.49
    浯
    0.49
     jours
    0.47
     fac
    0.47
    గాలు
    0.47
    gga
    0.46
    可怕
    0.46
    POSITIVE LOGITS
    \":
    0.56
    िन
    0.55
    ಿಯನ್
    0.55
    ланган
    0.55
     Asiatic
    0.55
    initely
    0.54
    $_{
    0.54
    ického
    0.53
    \".
    0.52
    -:
    0.52
    Activations Density 0.012%

    No Known Activations