© 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. 138717
    Prev
    Next
    INDEX
    Explanations

    different things to different people

    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
    ad
    0.78
    er
    0.58
     em
    0.56
     an
    0.55
    r
    0.52
    '
    0.51
     down
    0.50
     Australian
    0.50
     Konz
    0.49
     was
    0.49
    POSITIVE LOGITS
    کن
    0.57
    Teen
    0.55
    твер
    0.53
    ந்துள்ளது
    0.51
    Ꮰ
    0.51
    łącznie
    0.51
    ꞎ
    0.50
    金属
    0.50
    لاین
    0.49
    Кли
    0.49
    Activations Density 0.002%

    No Known Activations