© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216135
    Prev
    Next
    INDEX
    Explanations

    irrelevant to change

    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
     spielt
    0.40
     entangled
    0.39
     backpacks
    0.38
    ൊന്നും
    0.38
     ή
    0.35
     bermain
    0.35
     അല്ലെങ്കിൽ
    0.35
     weddings
    0.35
     或
    0.34
     spelen
    0.34
    POSITIVE LOGITS
    ПУ
    0.35
    Plot
    0.32
    доступ
    0.32
     Constru
    0.32
    Mechan
    0.31
    აშ
    0.31
     Plot
    0.31
    трибу
    0.30
    oidal
    0.30
     حقوق
    0.30
    Activations Density 0.004%

    No Known Activations