© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28830
    Prev
    Next
    INDEX
    Explanations

    location services or data

    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_10_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
    к
    0.76
    ä
    0.76
    än
    0.70
    oč
    0.70
    uliert
    0.69
    ing
    0.68
    uß
    0.67
    ளு
    0.67
    alom
    0.67
    üşt
    0.66
    POSITIVE LOGITS
    2
    0.73
     there
    0.70
    5
    0.69
    7
    0.69
     νο
    0.68
    9
    0.67
     validType
    0.65
     kilobytes
    0.63
     ২০২০
    0.63
    प
    0.63
    Activations Density 0.006%

    No Known Activations