© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126071
    Prev
    Next
    INDEX
    Explanations

    section breaks and comparision

    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_3_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
    ↵↵
    0.93
     an
    0.78
     A
    0.69
    _
    0.69
     I
    0.68
    A
    0.68
     are
    0.67
     এটি
    0.67
     is
    0.66
     S
    0.64
    POSITIVE LOGITS
    یم
    0.75
    ین
    0.72
    اک
    0.70
    oną
    0.70
    شون
    0.70
     صہی
    0.68
     لکھنے
    0.68
    یمو
    0.66
    ای
    0.66
    식회사
    0.65
    Activations Density 0.004%

    No Known Activations