© 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. 130627
    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
    1
    1.73
    ik
    1.40
    5
    1.37
    st
    1.27
    ni
    1.21
    im
    1.16
    na
    1.15
    ist
    1.13
    ata
    1.13
    4
    1.13
    POSITIVE LOGITS
    ل
    1.58
    ל
    1.48
    л
    1.39
    زي
    1.37
    ת
    1.36
    بي
    1.29
    jší
    1.27
    padă
    1.23
    يق
    1.23
    し
    1.21
    Activations Density 0.000%

    No Known Activations