© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 59889
    Prev
    Next
    INDEX
    Explanations

    say "Input"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    ,-\
    0.40
     \,\
    0.38
     nascetur
    0.37
     luscious
    0.36
     ascendent
    0.36
     sulfuric
    0.36
    apayati
    0.36
     closets
    0.35
     :',
    0.35
    Sdk
    0.35
    POSITIVE LOGITS
    sn
    0.70
    Sn
    0.70
     Sn
    0.67
     sn
    0.60
    SN
    0.58
     SN
    0.57
    <start_of_image>
    0.52
    Se
    0.52
    if
    0.49
     Se
    0.48
    Activations Density 0.004%

    No Known Activations