© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88624
    Prev
    Next
    INDEX
    Explanations

    accessory items

    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_23_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
     point
    0.21
     bâtiment
    0.21
    लाईन
    0.21
     hopper
    0.21
     ポイント
    0.20
    ㄛ
    0.20
     sò
    0.20
     профессор
    0.20
     Destiny
    0.20
     paging
    0.20
    POSITIVE LOGITS
    χν
    0.19
    rary
    0.19
    沟
    0.19
    favicon
    0.19
    crc
    0.18
    biased
    0.18
    的影响
    0.17
    rained
    0.17
    induced
    0.17
    pandas
    0.17
    Activations Density 0.002%

    No Known Activations