© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 183253
    Prev
    Next
    INDEX
    Explanations

    emphasizing "crucial" or "key"

    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_29_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
     अनु
    0.45
     финансо
    0.44
    AlignedText
    0.41
     المالية
    0.40
     Proceeds
    0.40
     वित्तीय
    0.39
     Sequences
    0.39
    叨
    0.38
    षित
    0.38
    organizations
    0.38
    POSITIVE LOGITS
     flattened
    0.46
     flattening
    0.46
     flatness
    0.44
     flat
    0.44
     barrels
    0.43
     barrel
    0.42
     room
    0.41
     vacuum
    0.41
    Kak
    0.41
    kak
    0.40
    Activations Density 0.009%

    No Known Activations