© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31375
    Prev
    Next
    INDEX
    Explanations

    currency, numbers, code, or punctuation

    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_31_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
     called
    0.50
     llamado
    0.37
    called
    0.36
     termed
    0.36
     Energie
    0.36
    叫做
    0.35
     ગુજરાત
    0.35
    )}=\
    0.34
     disebut
    0.34
     geometria
    0.34
    POSITIVE LOGITS
    ‥
    0.40
    ॅम्प
    0.39
    亅
    0.37
    スピ
    0.35
    ദേശം
    0.34
    ले
    0.33
    岫
    0.33
    લે
    0.32
    ೇ
    0.32
    教授
    0.32
    Activations Density 0.043%

    No Known Activations