© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43266
    Prev
    Next
    INDEX
    Explanations

    backrooms and streets

    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_3_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
     as
    0.80
     not
    0.73
    ON
    0.72
     t
    0.71
    ,
    0.69
     r
    0.68
     user
    0.68
    IA
    0.68
     but
    0.68
    3
    0.68
    POSITIVE LOGITS
    л
    0.86
    ak
    0.73
    ة
    0.73
    ле
    0.72
    ля
    0.71
    ية
    0.70
     postérieurs
    0.68
    ကြောင့်
    0.66
    ш
    0.66
    бе
    0.66
    Activations Density 0.002%

    No Known Activations