© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 204954
    Prev
    Next
    INDEX
    Explanations

    the number 1

    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_46_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
     Huyền
    0.39
     chronique
    0.38
     आने
    0.37
    ｯ
    0.37
    getNumber
    0.37
     vipp
    0.37
     નંબર
    0.37
    थिक
    0.36
    directly
    0.36
     Cus
    0.35
    POSITIVE LOGITS
     клад
    0.40
    teal
    0.37
     tertiary
    0.37
     taal
    0.37
     polarity
    0.36
    ("%.
    0.36
    ክት
    0.36
     خانو
    0.36
    르고
    0.36
    জাতি
    0.36
    Activations Density 0.001%

    No Known Activations