© 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. 131048
    Prev
    Next
    INDEX
    Explanations

    collection of

    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
     to
    1.41
     in
    1.13
    ↵
    1.07
     and
    1.02
     are
    0.97
    kan
    0.97
    den
    0.95
     be
    0.90
    kin
    0.89
     don
    0.88
    POSITIVE LOGITS
    رك
    1.23
    ਰ
    1.13
     welke
    1.10
    හ
    1.05
     Entonces
    1.03
    يد
    1.02
    شرين
    1.01
    릅
    1.01
     Enquanto
    0.98
    ولي
    0.98
    Activations Density 0.003%

    No Known Activations