© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117420
    Prev
    Next
    INDEX
    Explanations

    nutrition, flowers, vitality, best

    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_27_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
    燿
    0.44
    䫝
    0.40
     seguito
    0.39
     geometri
    0.39
     bölümde
    0.38
     الل
    0.35
     mandates
    0.35
     weighs
    0.35
    uates
    0.35
     compañeros
    0.35
    POSITIVE LOGITS
     nutrit
    0.43
     nourriture
    0.39
    栄養
    0.39
    꽃
    0.39
    ផ្
    0.39
     花
    0.37
    活力
    0.37
     최고의
    0.36
     maintien
    0.36
     꽃
    0.36
    Activations Density 0.009%

    No Known Activations