© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13469
    Prev
    Next
    INDEX
    Explanations

    mentions document content

    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_13_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
    -
    0.64
    ia
    0.53
    ka
    0.52
     massless
    0.50
    </h1>
    0.49
    immt
    0.49
    im
    0.48
    ima
    0.48
    ሜ
    0.47
     wrong
    0.47
    POSITIVE LOGITS
    ।*
    0.60
     řek
    0.55
     ഉണ്ടാ
    0.52
     Katherine
    0.52
     kinderen
    0.51
     〢
    0.51
     스트
    0.51
     pracovní
    0.51
     作業
    0.51
     Fuerza
    0.50
    Activations Density 0.004%

    No Known Activations