© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38800
    Prev
    Next
    INDEX
    Explanations

    logline:

    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_11_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
    糈
    0.61
    ете
    0.57
     реак
    0.57
     لكرة
    0.57
    дне
    0.57
    鹖
    0.57
     كرة
    0.56
    чника
    0.55
     관심
    0.54
     ஓடுப
    0.54
    POSITIVE LOGITS
     some
    0.69
    </h2>
    0.68
     de
    0.65
     je
    0.63
     to
    0.59
    s
    0.58
     trag
    0.56
    </td>
    0.54
     my
    0.54
     daily
    0.54
    Activations Density 0.011%

    No Known Activations