© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30846
    Prev
    Next
    INDEX
    Explanations

    Muni Maha

    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_7_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
     and
    0.48
     has
    0.47
    b
    0.45
    र
    0.45
    de
    0.44
     to
    0.43
    t
    0.42
    ল
    0.40
    d
    0.40
    е
    0.40
    POSITIVE LOGITS
     في
    0.46
    :
    0.39
     σε
    0.39
     الذين
    0.38
    ໃນ
    0.35
     இடையே
    0.35
    os
    0.34
     நேரம்
    0.33
    もあった
    0.33
    ルの
    0.33
    Activations Density 0.001%

    No Known Activations