© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12376
    Prev
    Next
    INDEX
    Explanations

    você precisa/gostaria

    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_40_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
     constituyen
    0.49
     incluyen
    0.44
     galería
    0.44
     región
    0.43
     constitución
    0.43
     lengua
    0.43
    疃
    0.43
     leng
    0.42
     jazy
    0.42
     origen
    0.41
    POSITIVE LOGITS
     é
    0.40
     mud
    0.39
    Cou
    0.38
    Mud
    0.38
     ficou
    0.38
     естественно
    0.37
     dizer
    0.37
     fica
    0.36
     reduzir
    0.36
     Oo
    0.36
    Activations Density 0.024%

    No Known Activations