© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34289
    Prev
    Next
    INDEX
    Explanations

    fostering something

    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_31_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
     недоста
    0.37
    ɮ
    0.37
     →
    0.36
     проводи
    0.36
     низкой
    0.36
     deficiency
    0.36
    ✧
    0.35
     நெ
    0.35
    :'],
    0.34
     массы
    0.34
    POSITIVE LOGITS
     cling
    0.40
     clings
    0.36
     division
    0.36
     Multiplication
    0.36
    ᆻ
    0.35
    osas
    0.35
    vention
    0.35
     multiplication
    0.35
     ხელისუფ
    0.35
    논
    0.35
    Activations Density 0.008%

    No Known Activations