© 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. 134059
    Prev
    Next
    INDEX
    Explanations

    curve or turn

    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
    DA
    1.15
    j
    1.15
    CS
    1.13
    RA
    1.12
    0
    1.06
    x
    1.06
    re
    1.05
     by
    1.05
    MI
    1.03
    MC
    1.02
    POSITIVE LOGITS
     científicos
    1.05
    ти
    1.04
    ్‌
    0.96
     поворо
    0.96
    くちゃ
    0.91
    辶
    0.90
    لے
    0.88
    có
    0.88
    сні
    0.86
    出して
    0.86
    Activations Density 0.001%

    No Known Activations