© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35007
    Prev
    Next
    INDEX
    Explanations

    bit manipulation

    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
    ↵
    0.86
     .
    0.65
    ca
    0.61
    că
    0.55
    can
    0.55
    ма
    0.54
    canic
    0.54
    ching
    0.52
    cana
    0.51
    Ev
    0.50
    POSITIVE LOGITS
    ن
    0.82
    ra
    0.77
    ן
    0.77
    ল
    0.75
    า
    0.73
    ovalo
    0.66
    ת
    0.66
    ל
    0.66
    ビット
    0.65
    ل
    0.64
    Activations Density 0.024%

    No Known Activations