© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133558
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    א
    1.16
    '
    1.13
    IA
    0.92
    .
    0.90
     اكتوبر
    0.86
     aplicativo
    0.85
     городов
    0.85
    אנ
    0.84
    ATORS
    0.84
    一只
    0.84
    POSITIVE LOGITS
    as
    1.52
     as
    1.40
    is
    1.32
    us
    1.24
    ing
    1.23
    um
    1.23
    u
    1.22
     with
    1.16
    ul
    1.09
    ä
    1.09
    Activations Density 0.000%

    No Known Activations