© 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. 32229
    Prev
    Next
    INDEX
    Explanations

    distributed key

    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
    확
    0.45
    ermodel
    0.43
    model
    0.41
     model
    0.40
     মডেল
    0.39
    NDA
    0.38
     शब्द
    0.36
    साय
    0.36
     व्याकरण
    0.36
    व्या
    0.36
    POSITIVE LOGITS
    訸
    0.41
     ойно
    0.41
     electing
    0.39
     Gabe
    0.38
    ເຮ
    0.38
     sesame
    0.37
     Zeke
    0.37
     Monster
    0.37
     gang
    0.37
     Zellen
    0.37
    Activations Density 0.001%

    No Known Activations