© 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. 37126
    Prev
    Next
    INDEX
    Explanations

    Tower of Hanoi and travel plans

    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
    ри
    1.25
    ur
    0.94
    urie
    0.78
    urp
    0.76
    '
    0.75
    urization
    0.73
    ाराम
    0.71
    ریان
    0.70
    urul
    0.70
    риев
    0.69
    POSITIVE LOGITS
     a
    0.87
    ف
    0.86
    ب
    0.82
    and
    0.77
     or
    0.73
    ق
    0.73
     \
    0.71
     e
    0.71
     tournaments
    0.70
    大
    0.70
    Activations Density 0.005%

    No Known Activations