© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17361
    Prev
    Next
    INDEX
    Explanations

    using punctuation like colons

    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_15_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
     مِن
    0.15
    ALL
    0.13
    గ్ర
    0.12
    <0xE7>
    0.12
    ет
    0.12
    ਲੇ
    0.12
    Gravity
    0.12
    :*
    0.12
    جن
    0.12
    ЕЛ
    0.12
    POSITIVE LOGITS
    th
    0.16
    odore
    0.15
    at
    0.14
    he
    0.14
     contemporaries
    0.14
    ethoven
    0.14
    kje
    0.13
     andere
    0.13
    contemporary
    0.13
    தைத்
    0.13
    Activations Density 0.152%

    No Known Activations