© 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. 5960
    Prev
    Next
    INDEX
    Explanations

    IIS, IRS, dir

    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
    त्रि
    0.43
    heading
    0.39
     trust
    0.38
    aine
    0.38
    Heading
    0.38
    صل
    0.37
     કહ
    0.37
    __*/
    0.37
    reme
    0.37
    apin
    0.37
    POSITIVE LOGITS
    日报
    0.42
     Kỳ
    0.41
     रुका
    0.38
     inputRange
    0.38
     หยุด
    0.37
     Bow
    0.37
    нета
    0.36
    权力
    0.36
    marginal
    0.36
    বিদেশ
    0.36
    Activations Density 0.019%

    No Known Activations