© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246961
    Prev
    Next
    INDEX
    Explanations

    styleUrls: ['./*.component.css']

    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_40_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
    ▎
    0.47
     Angola
    0.43
    Second
    0.42
    breadcrumbs
    0.41
    Ang
    0.38
     जावेद
    0.38
    __/
    0.38
    Madonna
    0.38
     Second
    0.36
    찍
    0.36
    POSITIVE LOGITS
     held
    0.43
    მის
    0.40
    空中
    0.40
     gm
    0.39
    وبت
    0.38
    omac
    0.38
    倝
    0.37
    珍
    0.36
    cole
    0.36
     धार
    0.36
    Activations Density 0.000%

    No Known Activations