© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11182
    Prev
    Next
    INDEX
    Explanations

    DEAs, model, thesis titles

    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_40_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
    yska
    0.39
    felder
    0.38
     INKA
    0.38
     तन
    0.36
    elya
    0.36
    켈
    0.36
     rans
    0.36
    гура
    0.35
     dogs
    0.35
     kalk
    0.34
    POSITIVE LOGITS
    triggers
    0.43
     triggers
    0.41
     joht
    0.40
     екс
    0.38
    둰
    0.38
    MID
    0.38
     nexus
    0.36
    चु
    0.36
     micro
    0.35
     Кита
    0.35
    Activations Density 0.041%

    No Known Activations