© 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. 158010
    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
    ि
    1.01
    િ
    0.96
    ре
    0.91
    िक
    0.88
    ան
    0.80
    리
    0.80
    터
    0.80
    ﺍ
    0.80
    ต่อ
    0.79
     as
    0.77
    POSITIVE LOGITS
     in
    1.25
    在
    1.11
    5
    1.05
    6
    1.05
     في
    1.02
    是
    0.97
    は
    0.97
    V
    0.96
    in
    0.96
    A
    0.96
    Activations Density 0.000%

    No Known Activations