© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28915
    Prev
    Next
    INDEX
    Explanations

    superstar or star

    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_10_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
    i
    0.35
    er
    0.30
    4
    0.28
    ed
    0.27
    com
    0.27
    1
    0.26
    a
    0.26
    8
    0.26
     It
    0.25
    ER
    0.25
    POSITIVE LOGITS
    s
    0.31
    ς
    0.27
    ের
    0.26
    ш
    0.21
    ों
    0.20
    sning
    0.20
    städ
    0.20
    ی
    0.19
    恝
    0.19
    %;
    0.18
    Activations Density 0.008%

    No Known Activations