© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58989
    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_2_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
    s
    1.02
    with
    1.01
    ших
    0.98
    h
    0.97
    ти
    0.85
    andering
    0.85
    ^{*}}
    0.85
    تى
    0.79
     Policies
    0.77
    GridLayout
    0.77
    POSITIVE LOGITS
    ก
    1.55
    ق
    1.18
    फ
    1.17
    ak
    1.15
     ไป
    1.15
    ع
    1.14
    ли
    1.13
     ने
    1.09
     as
    1.09
     were
    1.09
    Activations Density 0.000%

    No Known Activations