© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3604
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
    빼
    0.38
    Неза
    0.38
    utebol
    0.37
    organiser
    0.37
    encer
    0.37
    𝐲
    0.36
    បង្ហ
    0.35
    সিন
    0.35
    Criterion
    0.35
    錳
    0.35
    POSITIVE LOGITS
     making
    1.39
    Making
    1.29
     Making
    1.26
    making
    1.24
     membuat
    1.23
     make
    1.18
    make
    1.15
     MAKING
    1.13
     maken
    1.09
     made
    1.04
    Activations Density 0.055%

    No Known Activations