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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 203646
    Prev
    Next
    INDEX
    Explanations

    en-US locale and country codes

    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_25_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
    াজন
    0.44
    对称
    0.39
    delay
    0.39
     انصاف
    0.39
     একক
    0.38
     якості
    0.38
    equal
    0.37
     }=\
    0.37
    édération
    0.37
    㴓
    0.36
    POSITIVE LOGITS
     artificial
    0.38
     maf
    0.38
     Artificial
    0.38
     startup
    0.37
    िश्व
    0.36
     upotre
    0.35
    तीर्ण
    0.34
     organize
    0.34
     বেশকিছু
    0.33
     sáng
    0.33
    Activations Density 0.000%

    No Known Activations