© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 214626
    Prev
    Next
    INDEX
    Explanations

    architecture

    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_47_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
     Springs
    0.39
     proxim
    0.38
    ptor
    0.38
    ny
    0.38
     eo
    0.37
     Qo
    0.37
    wny
    0.37
     Q
    0.36
     pect
    0.35
    atoi
    0.35
    POSITIVE LOGITS
    大脑
    0.40
    閁
    0.38
     سرح
    0.38
     brain
    0.37
    抗
    0.37
    ওলানা
    0.37
    zIndex
    0.36
     Gracie
    0.36
    哒
    0.36
    腦
    0.36
    Activations Density 0.001%

    No Known Activations