© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 206233
    Prev
    Next
    INDEX
    Explanations

    code and JSON

    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_56_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
    थोरो
    0.38
     cpu
    0.37
    adece
    0.36
     musul
    0.36
     वइस
    0.35
    <unused57>
    0.35
     cubo
    0.35
    قامة
    0.35
     પસ
    0.34
     clogging
    0.34
    POSITIVE LOGITS
    ”,
    0.39
    ”(
    0.39
    辉
    0.38
    alas
    0.35
    letak
    0.34
    ”，“
    0.34
    </i>
    0.34
    ﷽
    0.34
    hale
    0.34
     аж
    0.33
    Activations Density 0.050%

    No Known Activations