© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49649
    Prev
    Next
    INDEX
    Explanations

    Fallout New Vegas

    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_31_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
     ortodox
    0.27
     BFS
    0.27
     IFS
    0.26
     SIC
    0.26
     padrões
    0.26
    ς
    0.26
     सिखा
    0.25
     utbild
    0.25
    ff
    0.25
     insegn
    0.25
    POSITIVE LOGITS
    하루
    0.27
     ایکسپریس
    0.25
    丙
    0.25
     Loh
    0.24
    рым
    0.24
     Ferd
    0.24
    Accommodation
    0.24
    roz
    0.24
    Discovery
    0.24
     Surveys
    0.24
    Activations Density 0.014%

    No Known Activations