© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207286
    Prev
    Next
    INDEX
    Explanations

    distance, comparisons, subsequent

    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_20_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
    Asalamualaikum
    0.15
    жни
    0.14
    granular
    0.14
     intents
    0.14
     dengan
    0.14
     principalTable
    0.14
    輳
    0.14
    adinam
    0.14
     sects
    0.14
    鏗
    0.14
    POSITIVE LOGITS
    _{
    0.17
    _
    0.15
     अधिकतम
    0.15
     the
    0.15
    lan
    0.14
    ğı
    0.13
    the
    0.13
    的时间
    0.13
    nå
    0.13
    )_{
    0.13
    Activations Density 0.002%

    No Known Activations