© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229243
    Prev
    Next
    INDEX
    Explanations

    online content symbols

    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
     تمام
    0.51
     चढ
    0.48
    :‏
    0.38
    쌓
    0.38
    共和
    0.37
    ¹,
    0.37
    Multimedia
    0.37
    Republican
    0.36
    STEM
    0.36
    ⠀⠀⠀⠀
    0.36
    POSITIVE LOGITS
     لعب
    0.75
     لق
    0.61
    )).
    0.49
    )),
    0.48
     لط
    0.46
    ))
    0.45
     playable
    0.45
     )),
    0.42
    ))`
    0.41
     ))
    0.40
    Activations Density 0.000%

    No Known Activations