© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231217
    Prev
    Next
    INDEX
    Explanations

    coding scheme

    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_6_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
    이었다
    0.88
    も
    0.81
    ্স
    0.80
    は
    0.80
    이었
    0.77
    pInBuffer
    0.74
     في
    0.73
     （
    0.68
    必須
    0.68
    Mga
    0.68
    POSITIVE LOGITS
     for
    1.03
     as
    1.01
    t
    0.98
    ل
    0.98
     they
    0.91
     that
    0.90
     are
    0.89
     of
    0.88
    are
    0.88
     every
    0.88
    Activations Density 0.001%

    No Known Activations