© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139957
    Prev
    Next
    INDEX
    Explanations

    websites

    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
    ậy
    0.40
     進
    0.39
     giallo
    0.37
     easy
    0.37
    issimus
    0.37
    ེ་
    0.37
    進
    0.36
     NIN
    0.35
    肺
    0.35
     จุด
    0.35
    POSITIVE LOGITS
    レル
    0.40
    bibitem
    0.40
    欉
    0.39
    aturamento
    0.38
    barrel
    0.38
     মুক্তিফ
    0.37
    WELL
    0.37
    ಧಿಕ
    0.37
     harapan
    0.37
     barrel
    0.36
    Activations Density 0.000%

    No Known Activations