© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1637
    Prev
    Next
    INDEX
    Explanations

    X followed by other characters

    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_39_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
    槟
    0.44
     الوحد
    0.43
    وده
    0.39
    rVert
    0.39
    scribed
    0.38
     "]";
    0.37
    STRONG
    0.37
    ováno
    0.36
    ৃহ
    0.36
    IdleSync
    0.36
    POSITIVE LOGITS
     xo
    0.44
    轴
    0.43
    oxo
    0.43
     X
    0.42
     XR
    0.41
     Z
    0.40
    ombie
    0.40
     Xen
    0.40
    ebra
    0.39
    eger
    0.39
    Activations Density 0.073%

    No Known Activations