© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196582
    Prev
    Next
    INDEX
    Explanations

    slavic suffixes like -ik and -inen

    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_4_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
    н
    0.15
    к
    0.14
    м
    0.13
    ш
    0.13
    In
    0.12
    wa
    0.12
     is
    0.12
    ’
    0.12
    th
    0.12
    .
    0.11
    POSITIVE LOGITS
    ない
    0.13
    al
    0.13
    ał
    0.12
    корд
    0.12
    bindingFields
    0.11
    ายเป็น
    0.11
    です
    0.11
    াভাব
    0.11
    ！)
    0.11
    deki
    0.11
    Activations Density 0.002%

    No Known Activations