© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20153
    Prev
    Next
    INDEX
    Explanations

    say "begin"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     số
    0.48
    号
    0.45
     IU
    0.40
     number
    0.40
     Titanium
    0.40
     TIT
    0.40
     tit
    0.38
     Bryson
    0.38
     Defining
    0.38
    ⴱ
    0.38
    POSITIVE LOGITS
    At
    1.04
     At
    1.03
     patch
    0.81
    patch
    0.79
    Patch
    0.77
     Patch
    0.71
    problem
    0.64
     patches
    0.63
     patching
    0.63
     problem
    0.62
    Activations Density 0.000%

    No Known Activations