© 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. 46058
    Prev
    Next
    INDEX
    Explanations

    VidIQ

    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
    ि
    0.60
    ة
    0.52
    з
    0.50
    ation
    0.49
    í
    0.48
     breaks
    0.47
     abatement
    0.47
    铒
    0.47
    い
    0.46
    z
    0.46
    POSITIVE LOGITS
     Fah
    0.48
     Deepak
    0.48
     Coon
    0.47
    amaran
    0.46
    onik
    0.46
    quillo
    0.44
    TimeTo
    0.44
    kwik
    0.43
     Bungal
    0.43
     Medina
    0.43
    Activations Density 0.000%

    No Known Activations