© 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
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 179356
    Prev
    Next
    INDEX
    Explanations

    laughter and informal text

    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
    irteenth
    0.39
     TOOL
    0.39
    ǒu
    0.39
    wana
    0.38
    Lj
    0.38
    agha
    0.37
    ጋ
    0.37
     Khanna
    0.36
     gevallen
    0.36
     imali
    0.36
    POSITIVE LOGITS
     Cairns
    0.38
    퐫
    0.37
    sten
    0.36
     Unt
    0.35
     dirt
    0.35
    фин
    0.35
    یف
    0.34
    Kai
    0.34
    quartz
    0.34
     Hebrews
    0.34
    Activations Density 0.000%

    No Known Activations