© 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. 216725
    Prev
    Next
    INDEX
    Explanations

    veteran

    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
     Terminator
    0.42
     ର
    0.41
    ActionListener
    0.41
     Eater
    0.40
     Therapeutics
    0.40
     Executors
    0.40
     resonators
    0.40
     Optimizer
    0.39
     Daytime
    0.39
    ulator
    0.38
    POSITIVE LOGITS
    ieron
    0.51
    sid
    0.40
     nincs
    0.40
    sdx
    0.38
    ---------------+
    0.38
    ოვანი
    0.37
    sic
    0.36
    Bats
    0.36
    rizzle
    0.35
    unlist
    0.35
    Activations Density 0.002%

    No Known Activations