© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5654
    Prev
    Next
    INDEX
    Explanations

    variation

    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_44_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
     FRANCIS
    0.43
    Francis
    0.42
     Francis
    0.40
    尕
    0.39
     состо
    0.38
    amard
    0.38
    크
    0.37
    urken
    0.36
     cubo
    0.36
    ziemy
    0.36
    POSITIVE LOGITS
     V
    0.57
    validate
    0.50
    V
    0.50
     validate
    0.50
    Verbose
    0.49
     Valentine
    0.48
     Vand
    0.48
    Validate
    0.47
    IOUS
    0.47
     Validate
    0.46
    Activations Density 0.080%

    No Known Activations