© 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. 11303
    Prev
    Next
    INDEX
    Explanations

    ripple effect

    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
    렐
    0.48
     ghép
    0.47
     عین
    0.47
    лли
    0.47
     తే
    0.46
    നോ
    0.46
    䚰
    0.46
    charging
    0.46
     glazing
    0.45
    ľad
    0.45
    POSITIVE LOGITS
    ាតុ
    0.51
    ۣ
    0.49
     AMA
    0.48
     sama
    0.47
     Rug
    0.47
     Ven
    0.45
     Petrol
    0.45
    าศ
    0.45
    披露
    0.45
    ългария
    0.44
    Activations Density 0.044%

    No Known Activations