© 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
    2. Gemma-3-27B-IT
    3. 22-GEMMASCOPE-2-TRANSCODER-262K
    4. 43965
    Prev
    Next
    INDEX
    Explanations

    collapse, packing, winding, condensation

    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
    able
    0.44
    .
    0.42
    -
    0.42
    ability
    0.41
     would
    0.41
    ());
    0.40
    hunt
    0.40
     -
    0.40
     specifics
    0.40
     side
    0.40
    POSITIVE LOGITS
     जीएसटी
    0.54
     협
    0.44
     공식
    0.44
    বৃত্তি
    0.43
     खोसला
    0.43
    ₲
    0.43
     χρη
    0.42
    थोरो
    0.42
     интегра
    0.42
    FlatStyle
    0.42
    Activations Density 0.002%

    No Known Activations