© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 57-GEMMASCOPE-2-TRANSCODER-262K
    4. 37526
    Prev
    Next
    INDEX
    Explanations

    specific subjects

    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
     Arb
    0.41
    ież
    0.38
    arán
    0.37
    𝙏
    0.37
    iye
    0.37
     праздник
    0.36
     விய
    0.36
     જરૂ
    0.35
     frightening
    0.35
     piled
    0.35
    POSITIVE LOGITS
    adamia
    0.38
    
    0.36
     खिला
    0.36
     solv
    0.36
     cupid
    0.35
    으로
    0.35
     starvation
    0.35
    매
    0.35
     vertreten
    0.35
     Remaining
    0.34
    Activations Density 0.000%

    No Known Activations