© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12002
    Prev
    Next
    INDEX
    Explanations

    exciton/excite

    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
    робнее
    0.39
     Mascot
    0.36
    cijas
    0.36
    🐁
    0.36
    abot
    0.35
     रत
    0.35
    gesetzt
    0.35
     carácter
    0.35
    などが
    0.34
     Scam
    0.33
    POSITIVE LOGITS
     beach
    0.45
     exc
    0.45
     에
    0.43
     chain
    0.43
     exchange
    0.42
     excit
    0.42
     cole
    0.41
    retch
    0.41
     échange
    0.41
     Exchange
    0.41
    Activations Density 0.020%

    No Known Activations