© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132776
    Prev
    Next
    INDEX
    Explanations

    noise-cancelling headphones

    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
    v
    1.66
    é
    1.41
    an
    1.40
    ra
    1.38
    ied
    1.36
    ill
    1.35
    h
    1.29
    1
    1.26
    int
    1.25
    ah
    1.24
    POSITIVE LOGITS
    。
    1.40
    ة
    1.02
    ።
    1.02
    يا
    0.95
     definizione
    0.93
    ת
    0.90
    只
    0.88
     clínica
    0.88
    ﭼ
    0.88
     في
    0.87
    Activations Density 0.000%

    No Known Activations