© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38859
    Prev
    Next
    INDEX
    Explanations

    various scripts and tokens

    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_11_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
     lysed
    0.50
     तारे
    0.49
    स्कृत
    0.46
     буквы
    0.45
     ModelAndView
    0.45
     самому
    0.44
    
    0.44
     zonas
    0.43
    廼
    0.43
    ."'
    0.43
    POSITIVE LOGITS
    fashion
    0.50
    frames
    0.50
    managers
    0.49
     forbidding
    0.48
    buton
    0.48
    inducing
    0.47
    ’),
    0.45
    fetching
    0.45
    burden
    0.45
    erçe
    0.45
    Activations Density 0.000%

    No Known Activations