© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17291
    Prev
    Next
    INDEX
    Explanations

    frequency throughout the day

    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_34_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
    未來
    0.37
     கை
    0.36
    plating
    0.36
     быстрее
    0.36
    reni
    0.36
     budú
    0.34
     départ
    0.33
    ("_
    0.33
     compatibles
    0.33
    ופי
    0.33
    POSITIVE LOGITS
    Throughout
    1.02
     Throughout
    0.99
     throughout
    0.98
     daytime
    0.84
     midday
    0.79
    ตลอด
    0.79
     하루
    0.76
     afternoon
    0.75
     morning
    0.74
     sepanjang
    0.74
    Activations Density 0.124%

    No Known Activations