© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140344
    Prev
    Next
    INDEX
    Explanations

    640x480 or resolution

    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_12_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
    id
    0.59
    it
    0.57
    ANG
    0.54
    7
    0.51
    wik
    0.50
    ersk
    0.49
    ang
    0.47
     Etc
    0.47
     inhibitors
    0.47
    litt
    0.47
    POSITIVE LOGITS
     tunnel
    0.45
     slumped
    0.44
     impressively
    0.44
     plunger
    0.43
     surpassed
    0.42
     debated
    0.42
     Vás
    0.41
    겸
    0.41
     surpass
    0.40
    ۇل
    0.40
    Activations Density 0.001%

    No Known Activations