© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10587
    Prev
    Next
    INDEX
    Explanations

    review summary

    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_13_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
    드
    0.22
     chup
    0.20
     اگر
    0.19
     trattano
    0.19
     سلام
    0.18
     머
    0.18
     nariz
    0.17
     נ
    0.17
     ގ
    0.17
    ード
    0.17
    POSITIVE LOGITS
     blocs
    0.17
     permitting
    0.17
    owy
    0.17
     Blocks
    0.16
    แหน่ง
    0.16
     Threatened
    0.16
     African
    0.15
    文化
    0.15
     clocked
    0.15
     threatened
    0.15
    Activations Density 0.004%

    No Known Activations