© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34843
    Prev
    Next
    INDEX
    Explanations

    my followed by relationship role

    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_31_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
    َوْ
    0.33
     വിവര
    0.32
    QUENCY
    0.30
     rapaz
    0.30
    ဵ
    0.30
     निश्च
    0.29
     olla
    0.29
     ধরন
    0.29
    ogr
    0.29
     कण
    0.29
    POSITIVE LOGITS
     મહે
    0.38
     nearest
    0.35
    宾
    0.35
    nearest
    0.34
     audience
    0.34
     buyer
    0.34
     парт
    0.31
    附近的
    0.31
    👥
    0.31
    귄
    0.31
    Activations Density 0.011%

    No Known Activations