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. 228955
    Prev
    Next
    INDEX
    Explanations

    solve equations

    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
    ieme
    0.38
    FlatStyle
    0.37
     -
    0.37
    bps
    0.37
    atee
    0.36
    દેશ
    0.35
    BoxLayout
    0.35
    baliknya
    0.35
    ─
    0.35
     평
    0.35
    POSITIVE LOGITS
     chiave
    0.39
    षण
    0.38
     Mine
    0.38
     claridad
    0.37
     ऑर्गेना
    0.36
    zza
    0.36
     KeyError
    0.36
    zać
    0.35
    اہم
    0.35
    ṓ
    0.35
    Activations Density 0.001%

    No Known Activations