© 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. 18947
    Prev
    Next
    INDEX
    Explanations

    validation, authentication, http

    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
     canvas
    0.39
     precio
    0.36
    濟
    0.35
     colonia
    0.35
    ื้อ
    0.34
     Alma
    0.34
    adple
    0.34
     skeleton
    0.34
    Colon
    0.34
    ੴ
    0.34
    POSITIVE LOGITS
    trendy
    0.41
    ='',
    0.38
    שי
    0.36
    filtering
    0.36
     trông
    0.36
    antro
    0.36
    abt
    0.36
    aksi
    0.35
    Authentication
    0.35
     괜찮
    0.35
    Activations Density 0.045%

    No Known Activations