© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6538
    Prev
    Next
    INDEX
    Explanations

    chapter topics or articles

    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_39_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
     supplementing
    0.35
    拍
    0.35
     papeles
    0.34
     Arya
    0.32
     reper
    0.32
     اض
    0.32
     puestos
    0.32
     size
    0.31
    reper
    0.31
    උ
    0.31
    POSITIVE LOGITS
    어도
    0.35
    weise
    0.35
    ப்பும்
    0.31
    ilius
    0.31
     अर्थव्यवस्था
    0.30
    طقة
    0.30
    낀
    0.30
     اقتصاد
    0.30
    씀
    0.30
     renewable
    0.29
    Activations Density 0.000%

    No Known Activations