© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24872
    Prev
    Next
    INDEX
    Explanations

    certain [descriptor]

    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_10_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
     в
    0.89
     destructor
    0.84
     от
    0.84
    А
    0.83
    ਾ
    0.82
     primeiro
    0.82
     first
    0.82
     exclu
    0.81
     barring
    0.81
    POSITIVE LOGITS
    z
    0.78
    j
    0.73
    centers
    0.72
    enhance
    0.71
    ke
    0.70
    eli
    0.70
    kes
    0.70
    ero
    0.70
    ff
    0.69
    stance
    0.69
    Activations Density 0.012%

    No Known Activations