© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51295
    Prev
    Next
    INDEX
    Explanations

    say "meeting" or "call" words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     chat
    0.42
    البه
    0.39
     chatting
    0.39
    chat
    0.38
    jir
    0.37
    ⓘ
    0.36
     ponder
    0.35
    亭
    0.35
    머니
    0.35
    (@"
    0.35
    POSITIVE LOGITS
     site
    0.42
     trips
    0.40
     SITE
    0.40
     Site
    0.39
     attendance
    0.39
    
    0.39
    foreground
    0.39
     Forums
    0.39
    Site
    0.39
     Bil
    0.38
    Activations Density 0.004%

    No Known Activations