© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11420
    Prev
    Next
    INDEX
    Explanations

    condemn and disclaimers

    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
     ល
    0.42
    doesn
    0.42
     no
    0.41
    morgan
    0.40
     није
    0.40
    אין
    0.40
    itively
    0.39
    侨
    0.39
    υχ
    0.38
    tidak
    0.38
    POSITIVE LOGITS
     pose
    0.54
     poses
    0.50
     posed
    0.42
     Pose
    0.42
     Inc
    0.41
     Disease
    0.40
     posing
    0.40
     ব্যাপারে
    0.38
     make
    0.38
    いだ
    0.38
    Activations Density 0.263%

    No Known Activations