© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15586
    Prev
    Next
    INDEX
    Explanations

    multiple times

    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_15_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
    er
    0.85
    h
    0.67
    sch
    0.63
    p
    0.63
    Smart
    0.62
    Linux
    0.61
    ر
    0.61
    Data
    0.60
    Ш
    0.59
    ड
    0.59
    POSITIVE LOGITS
     fiume
    0.62
     फू
    0.57
     inizio
    0.55
     kwa
    0.55
     oa
    0.53
     henne
    0.52
     stai
    0.52
     sõ
    0.51
     UCLA
    0.51
     jornal
    0.51
    Activations Density 0.024%

    No Known Activations