© 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. 206895
    Prev
    Next
    INDEX
    Explanations

    growth issue

    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
    ेंशन
    0.52
     características
    0.52
    自由に
    0.51
    ρές
    0.51
     CCL
    0.49
    𝘴
    0.48
     matière
    0.47
     expressões
    0.47
    특별시
    0.47
     Bajo
    0.46
    POSITIVE LOGITS
    കോ
    0.47
    寸
    0.45
    Hart
    0.44
    iod
    0.44
     omit
    0.43
    eroy
    0.43
    aty
    0.43
    ode
    0.43
    contain
    0.43
    assay
    0.42
    Activations Density 0.000%

    No Known Activations