© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37837
    Prev
    Next
    INDEX
    Explanations

    identify targets or properties

    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_11_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
     ಅತ್ಯ
    0.63
    ᱖
    0.57
    drawable
    0.56
     వైర
    0.56
     terbaru
    0.55
    போக்கு
    0.55
    пара
    0.55
     المثلث
    0.55
    respectively
    0.54
     britannique
    0.53
    POSITIVE LOGITS
    ul
    0.60
     da
    0.59
     i
    0.58
     AND
    0.57
    ano
    0.56
    af
    0.55
     ep
    0.54
     Agro
    0.53
    anc
    0.53
    奋
    0.52
    Activations Density 0.009%

    No Known Activations