© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 80036
    Prev
    Next
    INDEX
    Explanations

    fees, amounts, versions, tone, frameworks, temperature, bus, common

    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
     Highway
    0.27
     masterpieces
    0.27
     sch
    0.27
     benchmarks
    0.27
     maje
    0.26
     Road
    0.25
     z
    0.25
     cascades
    0.25
     fillings
    0.25
     Hari
    0.25
    POSITIVE LOGITS
    랗
    0.32
     vab
    0.30
    ridged
    0.28
    रोना
    0.28
    otically
    0.28
    ಗೋ
    0.28
    ទ្
    0.28
    TextMesh
    0.28
     విధంగా
    0.28
    biid
    0.28
    Activations Density 0.021%

    No Known Activations