© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105131
    Prev
    Next
    INDEX
    Explanations

    Cosa Nostra, 日本語

    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_1_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
    s
    1.59
    t
    1.37
    to
    1.28
    0
    1.27
    r
    1.21
    sp
    1.20
    ات
    1.20
    sd
    1.18
    k
    1.17
    ющие
    1.14
    POSITIVE LOGITS
     lessening
    1.06
     basically
    1.05
     makeshift
    1.00
     hideous
    1.00
    と考え
    0.98
     overclock
    0.98
     hurricane
    0.97
     highway
    0.96
     kerosene
    0.95
    𝕞
    0.93
    Activations Density 0.000%

    No Known Activations