© 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. 133934
    Prev
    Next
    INDEX
    Explanations

    SIFT feature matching

    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
    ના
    1.13
    し
    0.98
     CORPER
    0.95
    ());
    0.93
    も
    0.89
    әт
    0.88
    ও
    0.86
     കൂടുതൽ
    0.86
    ার্স
    0.84
    padă
    0.84
    POSITIVE LOGITS
    را
    1.19
    .
    1.10
     et
    1.07
    se
    1.06
    ik
    1.03
     was
    1.01
    ;
    1.01
    p
    0.93
     to
    0.91
    atik
    0.89
    Activations Density 0.000%

    No Known Activations