© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208503
    Prev
    Next
    INDEX
    Explanations

    forms of to be

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     gra
    0.43
    പ
    0.38
     comb
    0.37
    Enhanced
    0.36
    Improved
    0.35
    人々
    0.35
    Reduced
    0.35
    左
    0.35
    Ancestor
    0.34
     left
    0.34
    POSITIVE LOGITS
     path
    0.60
     indicated
    0.50
     indiqué
    0.45
     indicado
    0.45
     basePath
    0.45
     PATH
    0.44
     सादर
    0.43
     Pathfinder
    0.42
     indiquer
    0.42
     believed
    0.42
    Activations Density 0.003%

    No Known Activations