© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129834
    Prev
    Next
    INDEX
    Explanations

    bugs and insects

    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_1_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
    то
    1.03
    ון
    1.03
     for
    0.97
     on
    0.96
    ле
    0.96
    كره
    0.96
    s
    0.94
     obsahuje
    0.93
    т
    0.93
    ت
    0.93
    POSITIVE LOGITS
    -
    0.97
    0
    0.89
     झालेल्या
    0.84
    im
    0.78
     På
    0.77
    rom
    0.72
    istä
    0.71
    ऩ
    0.71
     ಮತ್ತ
    0.71
    4
    0.71
    Activations Density 0.001%

    No Known Activations