© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18821
    Prev
    Next
    INDEX
    Explanations

    this punctuation

    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
    issement
    0.35
    WP
    0.35
     lif
    0.34
    박
    0.34
     committed
    0.33
     quadrant
    0.33
    tsi
    0.33
    وپ
    0.33
    வி
    0.33
    urable
    0.33
    POSITIVE LOGITS
    ्सा
    0.42
     новости
    0.39
    ሄ
    0.38
     चेयर
    0.38
     ordinarily
    0.38
    дневно
    0.37
    Съ
    0.37
    irlik
    0.37
    rizioni
    0.37
    ديث
    0.37
    Activations Density 0.002%

    No Known Activations