© 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. 261161
    Prev
    Next
    INDEX
    Explanations

    “

    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
    ↵
    1.55
    い
    1.46
    an
    1.37
    ে
    1.23
    ia
    1.23
    P
    1.20
    em
    1.19
    ي
    1.18
    Message
    1.14
    i
    1.14
    POSITIVE LOGITS
     to
    1.41
    to
    1.30
    ال
    1.26
    "
    1.20
    ۰
    1.17
    "*
    1.15
     were
    1.11
    бра
    1.11
    were
    1.10
    פ
    1.10
    Activations Density 0.007%

    No Known Activations