© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13883
    Prev
    Next
    INDEX
    Explanations

    bare-root or root ball

    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_15_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
    akkhati
    0.55
     knih
    0.54
     협
    0.52
    赸
    0.51
     бизнеса
    0.50
     kuin
    0.50
    ekw
    0.50
     торговли
    0.49
    questa
    0.48
    肦
    0.48
    POSITIVE LOGITS
     Seafood
    0.51
    yser
    0.51
     fac
    0.50
    𝘵
    0.50
    Ṣ
    0.49
    એસ
    0.48
     Models
    0.48
     sorta
    0.48
    alsa
    0.47
    type
    0.47
    Activations Density 0.001%

    No Known Activations