© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11447
    Prev
    Next
    INDEX
    Explanations

    qualitative experience

    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_13_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
     mensen
    0.47
     erlebt
    0.46
    Unser
    0.46
     people
    0.46
     Often
    0.44
    ும்
    0.43
    )]
    0.43
     rarement
    0.43
     Lorsque
    0.42
     hadden
    0.42
    POSITIVE LOGITS
    ل
    0.44
    asius
    0.44
    री
    0.43
    していました
    0.43
    ចែកចាយ
    0.43
    سی
    0.43
    シャー
    0.43
    ilesh
    0.42
    okkaido
    0.42
     photospheric
    0.41
    Activations Density 0.001%

    No Known Activations