© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62154
    Prev
    Next
    INDEX
    Explanations

    products

    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_59_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
     for
    0.57
     were
    0.54
    ↵↵↵
    0.46
    s
    0.46
    """
    0.44
     from
    0.43
     by
    0.41
    ')
    0.41
    ↵
    0.39
    Net
    0.39
    POSITIVE LOGITS
    ∕
    0.43
     équipée
    0.42
     ಯಾವುದ
    0.40
     equipped
    0.39
     Australie
    0.39
    ષ્ય
    0.38
    அது
    0.38
    made
    0.38
    rolyte
    0.38
    誼
    0.38
    Activations Density 0.014%

    No Known Activations