© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130775
    Prev
    Next
    INDEX
    Explanations

    because it's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
    :
    0.94
    ել
    0.91
    ’
    0.91
    Α
    0.89
     مي‌
    0.84
     entsprechend
    0.83
    AM
    0.82
    US
    0.82
    С
    0.82
    ’).
    0.81
    POSITIVE LOGITS
    el
    1.05
    t
    0.94
    ل
    0.93
    é
    0.93
     to
    0.91
    d
    0.90
    g
    0.87
    li
    0.86
    im
    0.81
    st
    0.80
    Activations Density 0.028%

    No Known Activations