© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10032
    Prev
    Next
    INDEX
    Explanations

    many of the

    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_13_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
    ض
    0.19
    量
    0.17
     with
    0.17
    Learn
    0.17
     עם
    0.17
    แอ
    0.17
    ليزية
    0.16
    =""><
    0.16
    伊
    0.16
    OH
    0.16
    POSITIVE LOGITS
    temperatur
    0.21
    arze
    0.20
    nál
    0.20
     tervez
    0.19
    viar
    0.19
    ensatz
    0.19
    rafo
    0.19
    intero
    0.19
     governador
    0.19
    reiber
    0.18
    Activations Density 0.147%

    No Known Activations