© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45618
    Prev
    Next
    INDEX
    Explanations

    body problem

    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_22_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
    齙
    0.31
    نګه
    0.29
    стройки
    0.28
    чала
    0.27
     cellSize
    0.27
    ణులు
    0.26
    ولا
    0.26
    ಬಹುದ
    0.26
    孭
    0.26
    /#{
    0.25
    POSITIVE LOGITS
    k
    0.33
    Correspond
    0.29
     Frankfurt
    0.28
     मित्रता
    0.28
     Leipzig
    0.28
     memoirs
    0.27
    dés
    0.27
     Wahrheit
    0.27
     gên
    0.27
     xmas
    0.26
    Activations Density 0.000%

    No Known Activations