© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208758
    Prev
    Next
    INDEX
    Explanations

    MD

    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_56_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
    逹
    0.39
    ITwitter
    0.39
    Anch
    0.38
    養
    0.35
    뤽
    0.35
    িয়ের
    0.35
    𝓙
    0.35
    荪
    0.35
    ាយ
    0.34
    સર
    0.34
    POSITIVE LOGITS
    n
    1.23
     n
    1.18
    N
    1.16
    น
    1.13
    <0x98>
    1.10
    ن
    1.02
    ｎ
    0.99
    н
    0.93
    𝑛
    0.93
    न
    0.91
    Activations Density 0.001%

    No Known Activations