© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165309
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     كومونز
    0.45
     chunkSize
    0.43
     முடிவு
    0.42
    ults
    0.41
     fading
    0.39
    쓱
    0.39
    注入
    0.38
    getReference
    0.38
    Coor
    0.37
    步伐
    0.37
    POSITIVE LOGITS
     ادی
    0.38
    arum
    0.36
     Linguistics
    0.36
     communaut
    0.35
     अभिगमन
    0.35
     Charleston
    0.35
     öffentliche
    0.35
     organisms
    0.34
    Ἠ
    0.34
    enea
    0.34
    Activations Density 0.000%

    No Known Activations