© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32462
    Prev
    Next
    INDEX
    Explanations

    ch

    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_50_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
     Lom
    0.46
     ten
    0.43
    லோ
    0.42
    kül
    0.41
     suje
    0.40
     竹
    0.40
    िना
    0.40
     十
    0.39
    लो
    0.39
     ப்ளாக்
    0.39
    POSITIVE LOGITS
    nonpayable
    0.42
    illae
    0.42
    ypen
    0.40
    激光
    0.39
    andon
    0.39
    varande
    0.38
    scapes
    0.38
    acoli
    0.38
    ilia
    0.38
    embl
    0.37
    Activations Density 0.003%

    No Known Activations