© 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. 13533
    Prev
    Next
    INDEX
    Explanations

    domain names and code blocks

    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
     ý
    0.57
     magma
    0.55
     mogen
    0.55
     reflexión
    0.52
     lle
    0.52
     previewBuilder
    0.52
     waahanga
    0.52
     mengambil
    0.51
     sabiduría
    0.51
     walkway
    0.51
    POSITIVE LOGITS
    d
    0.64
    v
    0.60
    s
    0.53
    o
    0.45
    js
    0.43
    iseries
    0.42
    b
    0.42
    j
    0.42
    jn
    0.41
    fro
    0.41
    Activations Density 0.000%

    No Known Activations