© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237518
    Prev
    Next
    INDEX
    Explanations

    [/] links

    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_32_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
    沐
    0.44
     мем
    0.43
     Olive
    0.41
     মাধ্য
    0.40
     прось
    0.38
    Olive
    0.38
    METHOD
    0.37
    恐怖
    0.36
    uggest
    0.35
    昇
    0.35
    POSITIVE LOGITS
     television
    0.40
     invented
    0.39
     inaugurated
    0.39
    ેશન
    0.38
     illustration
    0.38
     regularity
    0.37
     disclosures
    0.37
     Illustrator
    0.37
     stare
    0.37
    purecounter
    0.37
    Activations Density 0.001%

    No Known Activations