© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41770
    Prev
    Next
    INDEX
    Explanations

    either or

    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_22_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
    گے
    0.47
    ੧
    0.47
    .”.
    0.46
     اهو
    0.44
    ."],
    0.44
     ajt
    0.44
    нії
    0.43
    Ẵ
    0.43
    濤
    0.43
    Slack
    0.43
    POSITIVE LOGITS
     contemporary
    0.43
     Contemporary
    0.43
     Another
    0.41
    autre
    0.39
     Cost
    0.38
     Crem
    0.37
     எழு
    0.37
     autre
    0.36
     other
    0.36
     context
    0.36
    Activations Density 0.002%

    No Known Activations