© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43892
    Prev
    Next
    INDEX
    Explanations

    end of an era

    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_3_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
    '
    0.95
    ’
    0.71
    ?
    0.68
    ।
    0.67
    ت
    0.66
    '।
    0.65
    ]
    0.64
     resins
    0.64
    تان
    0.64
    ト
    0.63
    POSITIVE LOGITS
    0
    0.92
    8
    0.79
    9
    0.73
    deki
    0.63
     auswählen
    0.61
    ATION
    0.58
    ния
    0.55
     Wege
    0.54
    ना
    0.54
    ند
    0.54
    Activations Density 0.000%

    No Known Activations