© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167469
    Prev
    Next
    INDEX
    Explanations

    wavelength

    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_56_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
    锣
    0.40
    위를
    0.37
    위
    0.37
    ตก
    0.35
    嘬
    0.35
     ورو
    0.34
    Ві
    0.34
    odikwa
    0.34
    дото
    0.34
    チン
    0.33
    POSITIVE LOGITS
     W
    3.11
    W
    2.08
     ال
    1.91
     डब्ल्यू
    1.63
    Ｗ
    1.54
     w
    1.38
    w
    1.34
    डब्ल्यू
    1.15
     В
    1.02
    𝐖
    0.97
    Activations Density 0.101%

    No Known Activations