© 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. 9375
    Prev
    Next
    INDEX
    Explanations

    turmeric

    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
    oring
    0.61
    <0xAC>
    0.47
    erton
    0.45
    icity
    0.45
    𝐨
    0.45
    ome
    0.44
    orph
    0.44
    elser
    0.44
     desplazamiento
    0.44
    cy
    0.44
    POSITIVE LOGITS
     Contributors
    0.48
     thisComponent
    0.46
    Ⲕ
    0.46
    <0xEA>
    0.46
    ็ก
    0.45
     Opinion
    0.45
     过
    0.45
    Protection
    0.45
    <=
    0.45
     Instructional
    0.44
    Activations Density 0.008%

    No Known Activations