© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195082
    Prev
    Next
    INDEX
    Explanations

    import tensorflow or keras layers

    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_27_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
     proble
    0.38
     probleem
    0.38
     فهم
    0.38
     Synchronization
    0.37
     België
    0.37
     परेशानियों
    0.37
     problemy
    0.37
    隘
    0.37
    初始化
    0.37
     वैधता
    0.37
    POSITIVE LOGITS
    tral
    0.35
     graze
    0.35
    拚
    0.34
    שר
    0.34
     peppermint
    0.34
    워크
    0.34
     అమ్మ
    0.34
    InitStructure
    0.34
     continueRoutine
    0.34
    쑤
    0.34
    Activations Density 0.000%

    No Known Activations