© 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. 58719
    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
    ك
    1.44
    ون
    1.31
    ل
    1.31
    كا
    1.26
     ότι
    1.24
    ల
    1.24
    ро
    1.23
    лі
    1.23
    كار
    1.23
    ุ
    1.23
    POSITIVE LOGITS
    is
    1.97
    in
    1.66
    n
    1.61
    at
    1.30
    ти
    1.27
    em
    1.22
    en
    1.20
    inę
    1.19
    ine
    1.18
    y
    1.18
    Activations Density 0.000%

    No Known Activations