© 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. 261158
    Prev
    Next
    INDEX
    Explanations

    specialized

    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
    as
    1.50
    い
    1.32
    кових
    1.17
    나
    1.16
    ート
    1.16
    та
    1.13
    며
    1.13
    માં
    1.11
    のは
    1.10
     플
    1.06
    POSITIVE LOGITS
    '
    1.70
    d
    1.61
    ه
    1.52
    r
    1.41
    1
    1.38
    ہ
    1.33
     for
    1.30
    تون
    1.27
    l
    1.27
    .
    1.23
    Activations Density 0.000%

    No Known Activations