© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 210273
    Prev
    Next
    INDEX
    Explanations

    X

    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_43_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
     Ratch
    0.38
     hed
    0.36
    𒊩
    0.36
    かん
    0.35
     Standard
    0.35
    çon
    0.34
    ûn
    0.34
    untza
    0.34
     покажу
    0.34
     Erweiter
    0.34
    POSITIVE LOGITS
     X
    1.14
    X
    1.04
    Ｘ
    0.71
    𝑋
    0.62
    Xd
    0.60
    Ⅹ
    0.60
     Х
    0.58
    Χ
    0.57
     Xs
    0.55
    nX
    0.53
    Activations Density 0.001%

    No Known Activations