© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6197
    Prev
    Next
    INDEX
    Explanations

    email services and publishing

    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_39_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
     algorithms
    0.42
     depuis
    0.40
     algorit
    0.39
     automat
    0.38
    겜
    0.38
    ന്യ
    0.38
    ͗
    0.37
    蒻
    0.37
     automatis
    0.37
     bapt
    0.37
    POSITIVE LOGITS
     cloud
    0.53
     Publishing
    0.52
    Cloud
    0.49
     Clouds
    0.48
     Cloud
    0.47
    cloud
    0.47
     publishing
    0.46
     Collaboration
    0.46
    云
    0.45
    Publish
    0.45
    Activations Density 0.256%

    No Known Activations