© 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. 162264
    Prev
    Next
    INDEX
    Explanations

    bragging

    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
     been
    1.24
    不
    1.14
     I
    1.13
     insolvent
    1.09
     gemeinsame
    1.09
    ارك
    1.05
     as
    1.02
    們
    1.02
     scrapped
    1.02
     synthes
    1.01
    POSITIVE LOGITS
    the
    1.43
    し
    1.39
    u
    1.34
    b
    1.20
    였
    1.20
    ast
    1.19
    il
    1.15
    baka
    1.14
    이었
    1.13
    The
    1.11
    Activations Density 0.000%

    No Known Activations