© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 194000
    Prev
    Next
    INDEX
    Explanations

    tech transfer

    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_9_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
     indiquer
    0.57
     elettronica
    0.57
    但
    0.55
     geändert
    0.53
     কিন্তু
    0.52
     effectuer
    0.52
     réaliser
    0.52
     aktivieren
    0.52
    ي
    0.50
    acionales
    0.50
    POSITIVE LOGITS
    BM
    0.55
    copper
    0.50
    rak
    0.50
    ired
    0.47
     divisions
    0.44
    ci
    0.44
    aling
    0.44
    INS
    0.44
     copper
    0.43
    lined
    0.43
    Activations Density 0.000%

    No Known Activations