© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195617
    Prev
    Next
    INDEX
    Explanations

    scale, localScale, setScale

    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_27_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
     アウター
    0.46
    FindAction
    0.44
    ލ
    0.43
     muchachos
    0.42
    ಟ್‌
    0.42
    UIntValue
    0.41
     ঘটন
    0.41
     knights
    0.41
     حیر
    0.41
     హీరో
    0.41
    POSITIVE LOGITS
    ar
    0.50
    a
    0.43
    </
    0.41
    apply
    0.41
    at
    0.41
    by
    0.41
    it
    0.40
    e
    0.39
     at
    0.39
     apply
    0.39
    Activations Density 0.000%

    No Known Activations