© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39460
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    親子
    0.40
     STEP
    0.38
    يطان
    0.38
     Сте
    0.37
     अल
    0.37
    步
    0.37
     вместо
    0.36
    STEP
    0.36
     生命周期函数
    0.35
     step
    0.35
    POSITIVE LOGITS
     front
    0.40
    囱
    0.38
     Front
    0.38
     সংখ্যাগ
    0.38
     Receive
    0.37
    汜
    0.37
    topping
    0.36
     Ob
    0.36
     Talk
    0.35
     Undert
    0.35
    Activations Density 0.000%

    No Known Activations