© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54384
    Prev
    Next
    INDEX
    Explanations

    essay about / on

    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_30_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
     పాల
    0.39
    ಿದ್ದೇನೆ
    0.39
     dressed
    0.39
     thơ
    0.38
     कराए
    0.38
     narrated
    0.37
    韻
    0.37
     superl
    0.36
     heartbeat
    0.36
     réserve
    0.36
    POSITIVE LOGITS
    Atlantic
    0.46
     December
    0.43
     Atlantic
    0.42
    วะ
    0.42
     Essay
    0.41
    Ultimate
    0.39
     Gupta
    0.39
    Essay
    0.38
     Citibank
    0.38
    程
    0.38
    Activations Density 0.005%

    No Known Activations