© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 139208
    Prev
    Next
    INDEX
    Explanations

    love and positive reinforcement

    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
    which
    0.61
    when
    0.57
    v
    0.56
    but
    0.56
     aggravate
    0.55
    ቮ
    0.54
    cuando
    0.53
    ва
    0.51
    vul
    0.50
    ecos
    0.50
    POSITIVE LOGITS
    ేష్
    0.72
     façon
    0.67
     PhD
    0.62
     Wiltshire
    0.62
    ᧐
    0.62
     Prefecture
    0.59
    OW
    0.58
     Corb
    0.57
     Cheshire
    0.56
     MALDI
    0.56
    Activations Density 0.001%

    No Known Activations