Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 57-GEMMASCOPE-2-TRANSCODER-262K
    4. 228945
    Prev
    Next
    INDEX
    Explanations

    code keywords

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     IS
    0.38
     IG
    0.38
    死
    0.37
     sekaligus
    0.37
    晿
    0.35
    ฺ
    0.35
     runaway
    0.34
    ŕ
    0.34
     Sada
    0.34
    sville
    0.34
    POSITIVE LOGITS
    enay
    0.44
    ﹙
    0.39
     हाम्रो
    0.39
     Grady
    0.37
    )。
    0.37
    》(
    0.37
    ours
    0.36
    िक्ष
    0.36
    iesel
    0.36
    Grady
    0.36
    Activations Density 0.000%

    No Known Activations