© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40359
    Prev
    Next
    INDEX
    Explanations

    Victor

    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_11_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
    cafe
    0.32
    lado
    0.31
    coupon
    0.31
    punkt
    0.31
     प्रॉब्लम
    0.30
    hab
    0.30
     書
    0.30
    hand
    0.30
    å
    0.30
    くなる
    0.29
    POSITIVE LOGITS
     as
    0.46
     IDs
    0.35
     altern
    0.33
     ASN
    0.32
     muc
    0.31
    สำหรับ
    0.31
     anima
    0.31
    谒
    0.30
     cambia
    0.30
     для
    0.30
    Activations Density 0.003%

    No Known Activations