© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139387
    Prev
    Next
    INDEX
    Explanations

    appears

    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_46_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
     included
    0.45
    included
    0.40
    Included
    0.38
     look
    0.38
     allowed
    0.38
    firm
    0.37
     starred
    0.37
    Ε
    0.37
    inv
    0.36
    <start_of_image>
    0.36
    POSITIVE LOGITS
    ambut
    0.43
     Voz
    0.41
    俔
    0.40
    偒
    0.39
     ডিভাইস
    0.38
     Mile
    0.38
     کاکروچ
    0.38
    尟
    0.38
     densidad
    0.38
     AMOUNT
    0.38
    Activations Density 0.001%

    No Known Activations