© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112707
    Prev
    Next
    INDEX
    Explanations

    organization names and identifiers

    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_2_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
    い
    1.51
    า
    1.39
    د
    1.33
    ви
    1.32
     is
    1.29
     on
    1.28
    ів
    1.27
    й
    1.27
    ла
    1.20
    ем
    1.20
    POSITIVE LOGITS
    0
    1.32
    ۰
    1.28
    ai
    1.11
    に向け
    1.10
    ments
    1.08
    ität
    1.01
    에
    1.00
    に
    0.99
     backend
    0.97
     τρόπο
    0.96
    Activations Density 0.001%

    No Known Activations