© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163558
    Prev
    Next
    INDEX
    Explanations

    cupcake without

    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_31_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
    ிற்க
    0.25
     ध्व
    0.23
    효
    0.22
     жүктөө
    0.22
    éon
    0.22
    iphon
    0.22
     Efect
    0.22
    펌
    0.22
    雯
    0.22
     Salad
    0.21
    POSITIVE LOGITS
    randrange
    0.24
     الْ
    0.23
     ತುಂಬಾ
    0.23
     명령
    0.22
    ቶ
    0.22
    𝑐
    0.22
    臨界
    0.22
    QtCore
    0.22
    Ə
    0.22
     cleared
    0.22
    Activations Density 0.001%

    No Known Activations