© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 66188
    Prev
    Next
    INDEX
    Explanations

    understand

    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_51_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
     Regan
    0.41
    アク
    0.40
     imong
    0.40
    腋
    0.39
    ஃப
    0.38
     karane
    0.37
    फ
    0.36
    druk
    0.36
     餐
    0.36
    आर
    0.35
    POSITIVE LOGITS
    ঈশ্বর
    0.44
    sqcup
    0.41
     GPI
    0.41
    Gp
    0.41
    icode
    0.40
    GP
    0.40
    Copy
    0.39
    gp
    0.39
     GP
    0.38
     copie
    0.38
    Activations Density 0.008%

    No Known Activations