© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261438
    Prev
    Next
    INDEX
    Explanations

    CSS property names and values

    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_5_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
    0
    1.84
    ۰
    1.48
    on
    1.39
    ।
    1.23
    ０
    1.22
    ן
    1.21
    می
    1.16
    soldiers
    1.16
    리
    1.13
    ।’
    1.13
    POSITIVE LOGITS
     (
    1.29
     （
    1.02
    }$,
    0.95
    使用
    0.95
     στον
    0.92
    ，
    0.90
    },
    0.89
    我
    0.88
     ممكن
    0.88
     campi
    0.88
    Activations Density 0.000%

    No Known Activations