© 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. 178219
    Prev
    Next
    INDEX
    Explanations

    class, Color, Counter

    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
     OAS
    0.41
    ells
    0.41
    mmas
    0.35
     inte
    0.35
     autop
    0.35
    kas
    0.34
     cáo
    0.34
    儲
    0.34
    urved
    0.34
     ecommerce
    0.34
    POSITIVE LOGITS
     bislang
    0.42
    Pig
    0.41
    Marg
    0.39
    ське
    0.38
    起き
    0.38
     río
    0.38
    岗
    0.38
    ready
    0.37
    τική
    0.36
     آبی
    0.36
    Activations Density 0.002%

    No Known Activations