© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51233
    Prev
    Next
    INDEX
    Explanations

    in-between states or a middle ground

    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_10_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
    0.34
     you
    0.31
     Warszawa
    0.30
     Tempat
    0.29
    0.29
    July
    0.28
     correlates
    0.28
    네
    0.28
    em
    0.28
     AVAILABLE
    0.28
    POSITIVE LOGITS
    вається
    0.27
    с
    0.25
    ү
    0.25
    ją
    0.25
    g
    0.24
    джа
    0.24
    on
    0.23
    ти
    0.23
    жи
    0.23
    stride
    0.23
    Activations Density 0.004%

    No Known Activations