© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130777
    Prev
    Next
    INDEX
    Explanations

    😊 and positive emojis

    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_1_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
    L
    1.65
    O
    1.48
    S
    1.38
    F
    1.34
    V
    1.34
    R
    1.30
    T
    1.28
    ت
    1.27
    E
    1.26
    。
    1.26
    POSITIVE LOGITS
    ו
    1.39
    으로
    1.14
     rafters
    1.09
    1.08
     urządzenia
    1.07
     dentures
    1.06
     mannequin
    1.04
     wildest
    1.04
     phạt
    1.03
     binoculars
    1.00
    Activations Density 0.000%

    No Known Activations