© 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. 32473
    Prev
    Next
    INDEX
    Explanations

    explanation or clarification

    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
     somehow
    0.75
     Somehow
    0.67
     somew
    0.47
     qualche
    0.41
    ByMerging
    0.40
    вні
    0.39
     irgendwie
    0.39
    颀
    0.36
    бні
    0.36
    蜿
    0.36
    POSITIVE LOGITS
     often
    0.43
     často
    0.38
     MLB
    0.37
     oldu
    0.37
     accountability
    0.36
    Une
    0.36
    Often
    0.35
     Wart
    0.35
    efully
    0.35
     часто
    0.35
    Activations Density 0.085%

    No Known Activations