© 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. 9255
    Prev
    Next
    INDEX
    Explanations

    black and white patterns

    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
    Wells
    0.46
    <sup>
    0.46
    PAN
    0.46
    Cancel
    0.45
    </h6>
    0.45
    <strong>
    0.44
     каждый
    0.44
    航
    0.43
    cation
    0.43
    *>
    0.43
    POSITIVE LOGITS
    模様
    0.50
     monochrome
    0.43
    色の
    0.42
     வெள்ளை
    0.42
     bianco
    0.41
     checkered
    0.40
    ორ
    0.40
    白色
    0.40
    гам
    0.40
    白的
    0.39
    Activations Density 0.024%

    No Known Activations