© 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. 111869
    Prev
    Next
    INDEX
    Explanations

    storm

    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
    ку
    1.66
    ни
    1.40
    ва
    1.40
    ри
    1.35
    त
    1.31
    к
    1.31
    ле
    1.20
    те
    1.19
    ט
    1.16
    на
    1.13
    POSITIVE LOGITS
    8
    1.16
    yards
    1.09
    af
    1.09
    otts
    1.07
    ple
    0.99
    ap
    0.97
    9
    0.96
    puted
    0.96
    emes
    0.95
    𝐠
    0.94
    Activations Density 0.000%

    No Known Activations