© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202621
    Prev
    Next
    INDEX
    Explanations

    2010

    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_12_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
    ς
    0.61
    ओं
    0.58
     reiterate
    0.53
     sépar
    0.52
     “[
    0.52
    이트
    0.51
    ittä
    0.50
     separating
    0.50
     ג
    0.49
     “
    0.49
    POSITIVE LOGITS
    ir
    0.58
    op
    0.58
    cards
    0.55
    her
    0.53
    light
    0.50
    cent
    0.50
    ,"
    0.50
    ri
    0.49
    ljen
    0.49
    decor
    0.48
    Activations Density 0.001%

    No Known Activations