© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35831
    Prev
    Next
    INDEX
    Explanations

    abbreviations or names

    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_50_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
    μός
    0.42
    mtq
    0.40
     Sequence
    0.40
     sequenced
    0.40
    畸
    0.40
     sequência
    0.39
    ériques
    0.38
     secuencia
    0.38
     sequence
    0.37
     tong
    0.37
    POSITIVE LOGITS
     gin
    0.46
    LP
    0.45
     Kings
    0.44
     Gin
    0.43
     L
    0.42
    TEC
    0.40
    Nin
    0.40
     Sprague
    0.39
    hauses
    0.39
    Gin
    0.39
    Activations Density 0.001%

    No Known Activations