© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37427
    Prev
    Next
    INDEX
    Explanations

    Parker Reynolds Palacio

    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_11_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
    akha
    0.57
     liczba
    0.54
    ваемых
    0.54
     није
    0.54
    वीस
    0.54
    љ
    0.53
    вших
    0.52
    wanath
    0.51
    umiem
    0.49
     vrijed
    0.48
    POSITIVE LOGITS
     etiology
    0.62
     observations
    0.58
     studies
    0.55
    畅
    0.54
    ES
    0.53
    s
    0.53
     subtitles
    0.52
     categ
    0.51
     demod
    0.51
     m
    0.50
    Activations Density 0.003%

    No Known Activations