© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213616
    Prev
    Next
    INDEX
    Explanations

    Echo

    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_47_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
     режима
    0.40
     hug
    0.39
     Hughes
    0.39
    aitre
    0.39
     steig
    0.38
     Werner
    0.37
    ville
    0.37
    태
    0.37
    рор
    0.37
    ranked
    0.37
    POSITIVE LOGITS
     Bay
    0.64
    Bay
    0.57
     bay
    0.55
     BAY
    0.55
    bay
    0.51
    BAY
    0.50
     Bayesian
    0.42
     Bays
    0.42
     අය
    0.39
    czych
    0.39
    Activations Density 0.002%

    No Known Activations