© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 211590
    Prev
    Next
    INDEX
    Explanations

    code file names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_43_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
     voilà
    0.37
    纤
    0.37
     친
    0.37
     Shipment
    0.36
     đón
    0.36
     Garnier
    0.35
    섬
    0.35
     voila
    0.35
     نسب
    0.34
     воро
    0.34
    POSITIVE LOGITS
    TableAdapter
    0.45
    MainActivityTest
    0.45
    唳
    0.42
    сторія
    0.40
     Nobel
    0.39
    Nob
    0.39
    UserController
    0.39
    HomeController
    0.39
    ListComponent
    0.38
    LoginActivity
    0.38
    Activations Density 0.001%

    No Known Activations