© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58816
    Prev
    Next
    INDEX
    Explanations

    implying

    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_11_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
    น
    0.71
    စဉ်
    0.60
    }$(
    0.59
    桃園
    0.58
    פ
    0.57
     variational
    0.57
    ﻜ
    0.57
     solenoid
    0.57
     supremely
    0.56
    בית
    0.56
    POSITIVE LOGITS
    ă
    1.01
    ors
    0.89
    ost
    0.86
    ate
    0.83
    ist
    0.83
    ari
    0.83
    ie
    0.80
    iy
    0.77
    ol
    0.77
    us
    0.77
    Activations Density 0.002%

    No Known Activations