© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 244612
    Prev
    Next
    INDEX
    Explanations

    AS $$ SQL syntax

    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
     [_
    0.41
     Jocelyn
    0.41
    进攻
    0.38
     SIST
    0.37
     المب
    0.37
     fileprivate
    0.36
    ∋
    0.36
     تو
    0.36
     október
    0.36
     uranyl
    0.36
    POSITIVE LOGITS
    radiation
    0.42
    Radiation
    0.42
    juice
    0.40
    ader
    0.38
    othe
    0.38
    adies
    0.37
    OVER
    0.37
    anças
    0.37
    vel
    0.37
     radiation
    0.37
    Activations Density 0.000%

    No Known Activations