© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53603
    Prev
    Next
    INDEX
    Explanations

    logged in as

    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_31_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
    rador
    0.39
     Englisch
    0.38
     पेट
    0.37
    廊
    0.35
    ोट
    0.35
    ्याज
    0.35
    투자
    0.34
     질문
    0.34
     exposing
    0.34
     투자
    0.33
    POSITIVE LOGITS
     accedere
    0.38
    桉
    0.38
     गहरे
    0.38
    Aware
    0.37
    isième
    0.36
    logs
    0.36
     করির
    0.36
    ⽇
    0.36
    login
    0.36
     সচেতন
    0.36
    Activations Density 0.001%

    No Known Activations