© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44681
    Prev
    Next
    INDEX
    Explanations

    backdoor access

    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_13_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
      
    0.63
    風
    0.50
    <i>
    0.46
    upa
    0.45
    ament
    0.45
     X
    0.45
     Move
    0.45
    thys
    0.45
    …
    0.44
     edit
    0.43
    POSITIVE LOGITS
     sasan
    0.63
     заповед
    0.59
    elevationMap
    0.58
    льд
    0.56
     precluded
    0.55
     Ива
    0.55
     پیغم
    0.55
    逪
    0.55
    <unused2068>
    0.55
     предотвра
    0.54
    Activations Density 0.000%

    No Known Activations