© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 196163
    Prev
    Next
    INDEX
    Explanations

    programming data structures

    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_26_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
    शो
    0.40
    )},
    0.40
    ,’’
    0.40
     ஓய்
    0.39
    df
    0.38
     founded
    0.38
    )],
    0.38
     Wyoming
    0.38
    ಳಿತ
    0.38
    ’’
    0.37
    POSITIVE LOGITS
     geral
    0.40
     sharps
    0.38
     Gerais
    0.37
     لندن
    0.37
    geb
    0.37
    をつ
    0.37
     wren
    0.37
    Karo
    0.37
    ॠ
    0.37
     dharm
    0.36
    Activations Density 0.000%

    No Known Activations