© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236075
    Prev
    Next
    INDEX
    Explanations

    type of

    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_32_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
    acritic
    0.36
    ৌত
    0.35
     snad
    0.35
    ੈ
    0.35
     ஒழு
    0.33
    OutputType
    0.33
     undisputed
    0.33
     Ztg
    0.33
    愣
    0.33
     éc
    0.32
    POSITIVE LOGITS
     Kac
    0.38
    शंकर
    0.38
     shir
    0.38
    kez
    0.37
    サロン
    0.37
     Василь
    0.36
    ਦੀ
    0.36
     RIC
    0.36
     δυνατό
    0.36
     VIC
    0.36
    Activations Density 0.006%

    No Known Activations