© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145369
    Prev
    Next
    INDEX
    Explanations

    DE suffix

    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_0_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
    é
    2.14
    en
    1.73
    á
    1.67
    n
    1.62
    i
    1.61
    ess
    1.59
    ad
    1.59
     a
    1.56
     I
    1.52
    od
    1.52
    POSITIVE LOGITS
    ၊
    1.62
    ם
    1.44
    ى
    1.42
    ،
    1.27
    ियों
    1.23
    телем
    1.23
     در
    1.22
     phận
    1.21
    시
    1.21
    MotionEvent
    1.17
    Activations Density 0.001%

    No Known Activations