© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53467
    Prev
    Next
    INDEX
    Explanations

    resolving challenges

    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_31_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
    чами
    0.33
    ля
    0.32
    DB
    0.32
     variantes
    0.32
     attain
    0.30
     मेंबर
    0.30
     табле
    0.30
    摜
    0.30
    utsche
    0.30
     سامان
    0.30
    POSITIVE LOGITS
     仮
    0.38
     kader
    0.35
     специа
    0.34
     специальные
    0.33
     special
    0.33
    假
    0.33
     Zulu
    0.32
     রাস
    0.32
    perd
    0.32
     परेशान
    0.32
    Activations Density 0.003%

    No Known Activations