© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61904
    Prev
    Next
    INDEX
    Explanations

    Jumping, Junk, Jargon, Japan, Jock

    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_2_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
    સ
    1.27
    い
    1.13
    د
    1.13
    л
    1.12
    q
    1.11
    स
    1.09
    м
    1.09
    م
    1.09
    ত
    1.09
    ل
    1.06
    POSITIVE LOGITS
    ุ
    1.21
    that
    1.16
     for
    1.13
     you
    1.11
     that
    1.10
     it
    1.03
    th
    1.02
    kan
    1.00
    1
    0.98
    mu
    0.93
    Activations Density 0.004%

    No Known Activations