© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117517
    Prev
    Next
    INDEX
    Explanations

    special characters and code dividers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
    inito
    0.38
    采
    0.38
     Schm
    0.38
     Wa
    0.37
     packed
    0.37
     altos
    0.36
     Luft
    0.36
     Bernstein
    0.35
    ียน
    0.35
     Wert
    0.35
    POSITIVE LOGITS
     blacklist
    0.44
    листы
    0.44
     ?";
    0.39
    blacklist
    0.38
    鋲
    0.38
    mare
    0.37
     oči
    0.37
     miała
    0.36
     teard
    0.36
     अनुभ
    0.36
    Activations Density 0.002%

    No Known Activations