© 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. 110079
    Prev
    Next
    INDEX
    Explanations

    Mojang Studios

    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_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
    in
    1.51
    c
    1.48
    ك
    1.31
    as
    1.30
    س
    1.29
    ية
    1.20
    Universität
    1.20
    ن
    1.18
    at
    1.16
    a
    1.15
    POSITIVE LOGITS
    .
    1.35
     DSLR
    1.06
    。
    0.93
     PRIME
    0.92
     INR
    0.89
    ม
    0.88
     А
    0.87
     NPV
    0.87
     SDR
    0.87
    0.87
    Activations Density 0.000%

    No Known Activations