© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78794
    Prev
    Next
    INDEX
    Explanations

    dew drops

    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_0_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
    sh
    1.86
    de
    1.85
    j
    1.82
    an
    1.77
    p
    1.74
    ing
    1.69
    리
    1.67
    y
    1.66
    ב
    1.59
    ру
    1.53
    POSITIVE LOGITS
    ка
    1.36
     primera
    1.20
     i
    1.17
     ejac
    1.16
     coded
    1.11
     gamb
    1.10
     poetic
    1.10
     gend
    1.09
     само
    1.08
     boa
    1.08
    Activations Density 0.000%

    No Known Activations