© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250903
    Prev
    Next
    INDEX
    Explanations

    C

    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
     crowning
    1.00
     crown
    0.96
     crowned
    0.93
     crowns
    0.93
    冠
    0.92
    Crown
    0.81
    crown
    0.79
     Crowns
    0.76
     hats
    0.75
     Crown
    0.70
    POSITIVE LOGITS
     C
    1.38
    C
    1.33
     câ
    1.23
    crow
    1.09
    c
    1.07
     crow
    1.06
     الص
    1.05
     Crow
    1.02
    setC
    0.98
    Crow
    0.96
    Activations Density 0.001%

    No Known Activations