© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61089
    Prev
    Next
    INDEX
    Explanations

    language capability

    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_59_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
    elt
    0.36
    මය
    0.36
    seated
    0.36
    řich
    0.36
    𝚎
    0.36
    layer
    0.35
     vaik
    0.34
    ivere
    0.34
    elian
    0.34
    TWI
    0.34
    POSITIVE LOGITS
     استف
    0.46
     ber
    0.45
     entitlement
    0.39
    suc
    0.38
    洸
    0.37
    冋
    0.37
     shod
    0.37
     suc
    0.37
    嘖
    0.36
     inadequate
    0.36
    Activations Density 0.000%

    No Known Activations