© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 196204
    Prev
    Next
    INDEX
    Explanations

    printf, fprintf, list, line, function calls

    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_26_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
    ش
    0.41
    م
    0.40
    </td>
    0.37
    채
    0.37
     채
    0.35
    </li>
    0.35
    Chứng
    0.34
     Channel
    0.34
    Generating
    0.34
     Ш
    0.34
    POSITIVE LOGITS
    ijska
    0.44
     Landry
    0.39
    PlatformImage
    0.38
    িঝ
    0.38
    ulents
    0.38
     milliamperes
    0.38
     könnte
    0.38
    incial
    0.38
    isierten
    0.38
    ώ
    0.38
    Activations Density 0.000%

    No Known Activations