© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236167
    Prev
    Next
    INDEX
    Explanations

    breakdown 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_25_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
     s
    0.35
     extending
    0.34
     tekint
    0.33
    ствен
    0.33
     extends
    0.32
     extend
    0.32
    cuk
    0.32
     gear
    0.32
     too
    0.31
     koje
    0.31
    POSITIVE LOGITS
    inuous
    0.39
    inous
    0.33
    veter
    0.33
    Occasionally
    0.33
    ivated
    0.32
    ▂
    0.32
     التأ
    0.32
    TypeOf
    0.31
    প্রথম
    0.31
     Tudo
    0.31
    Activations Density 0.014%

    No Known Activations