© 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. 82362
    Prev
    Next
    INDEX
    Explanations

    offering

    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
    نا
    1.70
     the
    1.48
    ه
    1.48
    ب
    1.46
     that
    1.45
    t
    1.41
    وا
    1.36
     it
    1.31
    s
    1.31
    sp
    1.28
    POSITIVE LOGITS
    four
    1.52
    ዎች
    1.40
    ф
    1.34
    founder
    1.31
    committee
    1.29
    COMPONENT
    1.27
    fc
    1.26
    at
    1.25
    ſe
    1.25
    ると
    1.23
    Activations Density 0.000%

    No Known Activations