© 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. 229251
    Prev
    Next
    INDEX
    Explanations

    0

    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
    𝑵
    0.40
    AES
    0.39
    सिया
    0.39
    erus
    0.39
     রাজি
    0.38
    ेन
    0.38
    েস
    0.37
    उदा
    0.36
     tron
    0.36
    Neu
    0.35
    POSITIVE LOGITS
     محافظ
    0.41
     eighteen
    0.40
     nineteen
    0.38
     fashionable
    0.38
    Zy
    0.37
    ’
    0.37
     seventeen
    0.36
     twenty
    0.36
    ظيف
    0.36
     EX
    0.35
    Activations Density 0.002%

    No Known Activations