© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159803
    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
     as
    1.88
    c
    1.41
    g
    1.24
    v
    1.24
    z
    1.16
     M
    1.15
     *
    1.10
     with
    1.09
     postulate
    1.09
    ad
    1.08
    POSITIVE LOGITS
    م
    1.63
    ри
    1.49
    大
    1.46
    ли
    1.45
    ح
    1.41
    ب
    1.41
    ي
    1.38
    ك
    1.38
    مي
    1.38
    مة
    1.35
    Activations Density 0.000%

    No Known Activations