© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124198
    Prev
    Next
    INDEX
    Explanations

    study plan

    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
     práct
    0.67
    ты
    0.64
    م
    0.62
    side
    0.61
    s
    0.59
    粹
    0.56
    з
    0.55
    ς
    0.54
     térm
    0.54
    دی
    0.53
    POSITIVE LOGITS
    '
    0.61
     original
    0.60
     Imam
    0.60
    akir
    0.59
     Ausgabe
    0.58
    amantha
    0.58
    า
    0.58
     maak
    0.56
    นาย
    0.56
     말씀을
    0.56
    Activations Density 0.000%

    No Known Activations