© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134003
    Prev
    Next
    INDEX
    Explanations

    element

    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
    c
    1.27
    p
    1.25
    ,
    1.25
    S
    1.18
    ف
    1.11
    T
    1.08
    L
    1.06
    R
    1.05
    E
    0.98
    ش
    0.97
    POSITIVE LOGITS
    们
    0.83
    に
    0.81
     โดย
    0.77
     mogao
    0.75
    ς
    0.74
     нього
    0.72
     কিছুর
    0.72
     رکھیں
    0.72
    ות
    0.71
    們
    0.71
    Activations Density 0.006%

    No Known Activations