© 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
    2. Gemma-3-27B-IT
    3. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 201142
    Prev
    Next
    INDEX
    Explanations

    names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     সেপ্ট
    0.39
    ໋
    0.39
    霖
    0.39
     Neub
    0.38
     Phú
    0.38
     ദിവ
    0.37
     रिसी
    0.37
     sores
    0.37
    புது
    0.37
    朩
    0.37
    POSITIVE LOGITS
     Sl
    0.38
     therm
    0.36
     выделить
    0.36
     pal
    0.35
    vascular
    0.35
     UAS
    0.35
    apol
    0.35
    quement
    0.34
    toctree
    0.34
     मिल
    0.34
    Activations Density 0.000%

    No Known Activations