© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131742
    Prev
    Next
    INDEX
    Explanations

    achingly

    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_1_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
     in
    1.76
     of
    1.29
     في
    1.20
    ли
    1.18
    ле
    1.12
    á
    1.11
    ä
    1.07
     is
    1.03
     be
    1.03
    ána
    0.98
    POSITIVE LOGITS
    a
    1.57
    ه
    1.31
    y
    1.27
    your
    1.25
    ↵↵
    1.21
    ा
    1.21
    دی
    1.20
    ে
    1.20
    सी
    1.19
    i
    1.18
    Activations Density 0.001%

    No Known Activations