© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204706
    Prev
    Next
    INDEX
    Explanations

    embodiment

    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_6_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
    y
    1.70
    p
    1.45
    ;
    1.33
    f
    1.30
    o
    1.29
    TE
    1.28
    ight
    1.25
    A
    1.24
    SI
    1.20
    MA
    1.20
    POSITIVE LOGITS
    ин
    1.26
    이스
    1.13
    ан
    1.09
     présente
    1.05
    ات
    1.04
    بي
    1.00
     qualité
    1.00
    у
    1.00
     humains
    1.00
     dầu
    0.99
    Activations Density 0.000%

    No Known Activations