© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214950
    Prev
    Next
    INDEX
    Explanations

    laundry room

    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_5_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
    n
    1.86
    ।
    1.51
    q
    1.50
    d
    1.46
    ។
    1.45
    ي
    1.42
    ৮
    1.41
    j
    1.41
    of
    1.37
    v
    1.37
    POSITIVE LOGITS
    ți
    1.19
    ’,
    1.14
    ıyla
    1.05
     naturalist
    0.97
     quedan
    0.95
    N
    0.95
    ার
    0.93
     doivent
    0.93
     chinois
    0.93
     consejo
    0.93
    Activations Density 0.000%

    No Known Activations