© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18104
    Prev
    Next
    INDEX
    Explanations

    sure

    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_15_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
     cibo
    0.58
     }}>
    0.50
    EO
    0.50
    他の
    0.50
     render
    0.49
     sezione
    0.49
    同じ
    0.47
     vero
    0.47
     foro
    0.47
     pono
    0.47
    POSITIVE LOGITS
     blazing
    0.58
    ွှ
    0.57
    ष्टा
    0.56
    pherds
    0.55
    isements
    0.55
     barrels
    0.53
     orchards
    0.52
    ucht
    0.52
    驸
    0.51
     vaults
    0.51
    Activations Density 0.010%

    No Known Activations