© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 10236
    Prev
    Next
    INDEX
    Explanations

    one [way, look, step, of, World, example, might, important, reason]

    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_40_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
     thing
    0.41
     후
    0.39
     केमिस्ट्री
    0.39
     chemistry
    0.39
     şekilde
    0.39
    ismen
    0.39
     ces
    0.38
     AFTER
    0.38
    후
    0.38
     dopo
    0.38
    POSITIVE LOGITS
    ory
    0.39
    щаются
    0.36
    тивний
    0.36
     tret
    0.36
    INITIAL
    0.36
    -}
    0.35
    getInt
    0.35
     אחד
    0.35
    ụy
    0.35
     одном
    0.34
    Activations Density 0.046%

    No Known Activations