© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 194659
    Prev
    Next
    INDEX
    Explanations

    links and citations

    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
     غير
    0.39
     غیر
    0.38
    Alt
    0.38
     ADD
    0.38
     medium
    0.37
     Alt
    0.36
     U
    0.36
     অন
    0.35
     Montgomery
    0.35
     Medium
    0.35
    POSITIVE LOGITS
    Thickness
    0.41
    ේව
    0.41
    BEAN
    0.40
    ylobacter
    0.40
    تیب
    0.39
     యొక్క
    0.39
    ENDO
    0.38
    क्रो
    0.38
     வண்ணப்பூ
    0.38
     menghasilkan
    0.37
    Activations Density 0.000%

    No Known Activations