© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39856
    Prev
    Next
    INDEX
    Explanations

    and preceding 'put' or 'dar'

    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
     solvable
    0.65
    ви
    0.64
    ومان
    0.63
    ಬ್ಬಿಣ
    0.63
    ز
    0.59
    ни
    0.58
     symplect
    0.58
    现代化
    0.58
    渟
    0.57
    льд
    0.57
    POSITIVE LOGITS
    ly
    0.79
    D
    0.78
    ?
    0.76
     And
    0.75
    ing
    0.74
    C
    0.73
     D
    0.73
      
    0.72
    ane
    0.72
    ed
    0.71
    Activations Density 0.028%

    No Known Activations