© 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. 44051
    Prev
    Next
    INDEX
    Explanations

    Hamiltonian paths

    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
    ad
    0.79
    '
    0.70
    (
    0.69
     A
    0.66
    aps
    0.66
    ende
    0.66
    g
    0.65
    ya
    0.65
    ills
    0.63
    lig
    0.63
    POSITIVE LOGITS
    ק
    1.08
    ມັນ
    0.93
    نین
    0.90
    ین
    0.87
    ک
    0.84
    いた
    0.82
    られた
    0.79
    ら
    0.78
     بین
    0.77
    که
    0.76
    Activations Density 0.008%

    No Known Activations