© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50112
    Prev
    Next
    INDEX
    Explanations

    requests for specific items or information

    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_30_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
     हूँ
    0.37
     Shrine
    0.34
     presentan
    0.34
     bất
    0.33
     క్రి
    0.32
     થઈ
    0.32
    shr
    0.32
    ൫
    0.32
     свет
    0.31
    Courtesy
    0.31
    POSITIVE LOGITS
    ផលិត
    0.44
     CHANNEL
    0.42
     InputAction
    0.39
    璽
    0.39
     exponent
    0.38
    ิม
    0.38
    <0xC4>
    0.38
     নিয়োগ
    0.37
     ảo
    0.37
     spermato
    0.37
    Activations Density 0.013%

    No Known Activations