© 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
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 167591
    Prev
    Next
    INDEX
    Explanations

    2

    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
     х
    0.45
     ६
    0.38
     ૧
    0.38
    emap
    0.38
     ৭
    0.37
    CSC
    0.37
     भी
    0.36
     २
    0.36
    itatis
    0.36
     ១
    0.36
    POSITIVE LOGITS
     different
    0.42
    different
    0.40
     exceed
    0.37
     diferente
    0.37
    Different
    0.37
    MktCap
    0.37
     不同
    0.36
     வெவ்வேறு
    0.36
    市场上
    0.35
    Semester
    0.35
    Activations Density 0.001%

    No Known Activations