© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 33390
    Prev
    Next
    INDEX
    Explanations

    he followed by month/day

    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_7_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
    S
    0.79
    <0x80>
    0.72
    B
    0.63
    是怎么
    0.61
    K
    0.60
    н
    0.58
    ை
    0.57
    要想
    0.57
     može
    0.55
     sería
    0.55
    POSITIVE LOGITS
    ні
    0.83
     in
    0.82
    ды
    0.72
    dan
    0.71
     as
    0.65
    ต์
    0.65
    ﻥ
    0.64
    ных
    0.64
    ный
    0.63
    𝗺
    0.63
    Activations Density 0.000%

    No Known Activations