© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117998
    Prev
    Next
    INDEX
    Explanations

    phases or stages

    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_27_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
    Falls
    0.40
     jacks
    0.39
     vontade
    0.38
    른
    0.38
    릅
    0.37
    Favorites
    0.36
    젬
    0.36
     옷
    0.35
     اجمعين
    0.35
    ན
    0.35
    POSITIVE LOGITS
    uer
    0.44
    upol
    0.40
    udian
    0.38
     Supervisory
    0.36
     reliability
    0.36
     ঘোষ
    0.36
    sonsten
    0.36
     conserved
    0.35
     funcion
    0.34
    હેરા
    0.34
    Activations Density 0.004%

    No Known Activations