© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 158207
    Prev
    Next
    INDEX
    Explanations

    they say

    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_50_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
    राट
    0.37
    ඹ
    0.35
    вить
    0.34
     Augusta
    0.34
    ቀት
    0.34
    ]^{\
    0.33
    ="../../../
    0.32
    |^{\
    0.32
    վել
    0.32
    ὀ
    0.32
    POSITIVE LOGITS
     maxim
    1.99
     saying
    1.70
     adage
    1.69
     Maxim
    1.61
    Maxim
    1.57
    maxim
    1.56
     max
    1.55
     Saying
    1.52
     Max
    1.52
     proverb
    1.50
    Activations Density 0.001%

    No Known Activations