© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79373
    Prev
    Next
    INDEX
    Explanations

    test cases input

    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_31_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
     craftsmanship
    0.38
    囘
    0.37
     gravy
    0.36
    イン
    0.36
    lena
    0.36
     Russian
    0.35
    $-,
    0.35
     russian
    0.35
     sedimentary
    0.35
     convertView
    0.35
    POSITIVE LOGITS
    परा
    0.41
    FNO
    0.39
     அனுப்ப
    0.36
    Operation
    0.36
    childNodes
    0.35
     الماس
    0.35
    ຢ່າງ
    0.35
    矶
    0.34
    游
    0.34
     grounded
    0.34
    Activations Density 0.001%

    No Known Activations