© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43580
    Prev
    Next
    INDEX
    Explanations

    presenting options

    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_22_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
     _;
    0.39
    ែម
    0.38
     hedging
    0.35
     arbitration
    0.34
     Arbitration
    0.34
     concernant
    0.33
    фициа
    0.33
     hedges
    0.32
    owicz
    0.32
     signalling
    0.32
    POSITIVE LOGITS
    десь
    0.31
     八
    0.30
     defecto
    0.30
    ITTER
    0.29
     incubated
    0.29
    八
    0.29
     النموذج
    0.28
    ্মার
    0.28
    思
    0.28
     ஐந்து
    0.28
    Activations Density 0.026%

    No Known Activations