© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31684
    Prev
    Next
    INDEX
    Explanations

    randomized controlled trials

    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_7_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
     be
    1.06
    0.93
    ä
    0.79
     metabolism
    0.77
     garden
    0.76
     pulley
    0.75
     verb
    0.75
     is
    0.74
     well
    0.74
     revolution
    0.74
    POSITIVE LOGITS
    t
    1.24
    𝚙
    1.06
    न
    1.02
    К
    0.95
    tdd
    0.93
    stituto
    0.92
    ᵚ
    0.91
    вых
    0.85
     Australie
    0.85
    AN
    0.85
    Activations Density 0.001%

    No Known Activations