© 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. 232737
    Prev
    Next
    INDEX
    Explanations

    Caldwell; trim level

    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
    с
    1.04
    س
    1.01
    お
    0.90
    ή
    0.89
    نش
    0.88
    一颗
    0.85
    า
    0.85
    سور
    0.83
    了他的
    0.82
    RA
    0.82
    POSITIVE LOGITS
    ri
    1.20
    v
    1.12
    ol
    1.00
    ла
    0.95
    lige
    0.91
    l
    0.87
    ри
    0.86
    ra
    0.84
    wl
    0.82
    ant
    0.82
    Activations Density 0.000%

    No Known Activations