© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163969
    Prev
    Next
    INDEX
    Explanations

    whenever possible

    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_31_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
     அடிக்கடி
    0.36
     frecu
    0.35
    
    0.34
    LEM
    0.33
    AUTH
    0.32
     বদলে
    0.32
    Fetch
    0.31
    焲
    0.31
    Bats
    0.30
     चला
    0.30
    POSITIVE LOGITS
     apologize
    0.38
    কেট
    0.35
    )}{\
    0.35
     characterize
    0.35
     Girl
    0.34
     prioritize
    0.33
     પહો
    0.33
     Weeks
    0.32
     Empire
    0.32
     sympathize
    0.32
    Activations Density 0.002%

    No Known Activations