© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130192
    Prev
    Next
    INDEX
    Explanations

    NMF

    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_6_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
    that
    1.19
    and
    1.08
    r
    1.04
    К
    1.00
    ة
    0.98
    t
    0.98
    st
    0.93
    я
    0.90
    Е
    0.88
    to
    0.86
    POSITIVE LOGITS
    ي
    1.05
     oeuvre
    0.93
     pathos
    0.91
     patina
    0.91
    en
    0.89
     num
    0.89
     sabbatical
    0.88
    i
    0.87
     lamina
    0.86
     Department
    0.86
    Activations Density 0.000%

    No Known Activations