© 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. 130845
    Prev
    Next
    INDEX
    Explanations

    Captain James Cook

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    g
    1.20
    ill
    1.18
    c
    1.18
    ad
    1.14
    st
    1.10
    cr
    1.09
    sh
    1.08
    irin
    1.08
    ind
    1.06
    arı
    1.05
    POSITIVE LOGITS
    ي
    1.17
    ينا
    1.15
    ו
    1.13
    ريك
    1.08
    يها
    1.07
    ري
    1.06
    يي
    1.03
    كره
    1.01
    كا
    1.01
    多
    1.00
    Activations Density 0.000%

    No Known Activations