© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 91830
    Prev
    Next
    INDEX
    Explanations

    technical fragments

    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_60_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
     development
    0.42
     phenomenon
    0.41
     promotion
    0.41
    Z
    0.40
     decomposition
    0.39
     creation
    0.39
     preprocessing
    0.39
     encryption
    0.38
    z
    0.38
     exception
    0.38
    POSITIVE LOGITS
    édrale
    0.38
    ρίς
    0.37
    cedented
    0.37
    ísima
    0.36
    IDENTAL
    0.36
     Ó
    0.35
    IFIED
    0.35
    itió
    0.35
    ised
    0.35
    isés
    0.35
    Activations Density 0.000%

    No Known Activations