© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 214066
    Prev
    Next
    INDEX
    Explanations

    diverse scripts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
     Fo
    0.44
    Fo
    0.44
    0.43
     barrel
    0.42
     RPG
    0.39
     Funk
    0.39
    Png
    0.38
    Funk
    0.38
    ʁ
    0.38
    casts
    0.38
    POSITIVE LOGITS
     羽
    0.41
    媳
    0.40
    λώ
    0.39
    ᒥ
    0.39
     зим
    0.39
    دو
    0.38
    tableau
    0.37
     يزيد
    0.37
    焱
    0.37
     выбира
    0.37
    Activations Density 0.009%

    No Known Activations