© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45090
    Prev
    Next
    INDEX
    Explanations

    prioritize proper form

    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_22_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
     המש
    0.40
    κι
    0.38
     ઉજ
    0.35
    ivant
    0.34
     teh
    0.34
    s
    0.34
    ज़
    0.34
    篁
    0.34
    qPCR
    0.33
    jour
    0.33
    POSITIVE LOGITS
     говорит
    0.42
     mirrors
    0.40
     führt
    0.40
    <0xE3>
    0.39
     Mirrors
    0.39
     badly
    0.39
     door
    0.39
     widz
    0.38
     unity
    0.38
     first
    0.38
    Activations Density 0.000%

    No Known Activations