© 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. 106392
    Prev
    Next
    INDEX
    Explanations

    model numbers and specs

    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
    杯
    0.47
     Cup
    0.44
    Cup
    0.43
    隔离
    0.43
     cup
    0.42
     रॉय
    0.42
    ദി
    0.42
    促
    0.41
    cup
    0.40
    컵
    0.40
    POSITIVE LOGITS
     Mare
    0.41
    High
    0.38
     glu
    0.38
    Mare
    0.38
     LQ
    0.37
    BrNO
    0.37
     brochures
    0.36
    ENTO
    0.36
    Brist
    0.36
    Blood
    0.36
    Activations Density 0.000%

    No Known Activations