© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43513
    Prev
    Next
    INDEX
    Explanations

    Click Me

    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_3_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
    uments
    0.76
    á
    0.76
    ü
    0.76
    It
    0.71
    Validators
    0.71
    se
    0.70
    akai
    0.70
     It
    0.70
    ja
    0.69
    ub
    0.68
    POSITIVE LOGITS
     tıkl
    0.77
     clicking
    0.75
     click
    0.71
    <0xBB>
    0.68
     взя
    0.67
    <0xAC>
    0.66
     cliquer
    0.63
     prospectus
    0.62
    <0x99>
    0.61
     функції
    0.61
    Activations Density 0.001%

    No Known Activations