© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167475
    Prev
    Next
    INDEX
    Explanations

    relevant today

    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_34_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
    ণ্ট
    0.45
    œuvre
    0.39
    难
    0.37
    aap
    0.36
     gabb
    0.35
     Esperanza
    0.35
    edges
    0.34
    Edge
    0.34
     œuvre
    0.34
    ApiResponse
    0.34
    POSITIVE LOGITS
    設定
    0.44
    Oreal
    0.42
     flick
    0.38
     सचिवा
    0.38
     Flick
    0.37
    backward
    0.37
    醾
    0.37
    Backward
    0.36
     prenot
    0.36
    PSC
    0.35
    Activations Density 0.004%

    No Known Activations