© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7158
    Prev
    Next
    INDEX
    Explanations

    close your eyes

    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
     closed
    0.44
    闭
    0.42
     cerrada
    0.42
     zamknię
    0.40
    Closed
    0.40
     menutup
    0.39
     cierra
    0.38
    VV
    0.38
    要么
    0.38
     Closed
    0.37
    POSITIVE LOGITS
    getSize
    0.39
     Um
    0.39
    рист
    0.37
    grad
    0.37
    GRAD
    0.36
     grad
    0.35
     छ
    0.35
    minded
    0.35
     peine
    0.35
    gradle
    0.34
    Activations Density 0.008%

    No Known Activations