© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175990
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_24_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
    ith
    0.48
    stä
    0.46
    anz
    0.44
    fen
    0.43
    ulai
    0.43
    ी
    0.42
     href
    0.42
     urine
    0.42
    ff
    0.42
    cre
    0.42
    POSITIVE LOGITS
    шње
    0.52
    хоро
    0.52
     номера
    0.50
    DummyView
    0.50
    らない
    0.49
     adatto
    0.48
    eway
    0.48
     GoObject
    0.48
     Liên
    0.47
    洿
    0.47
    Activations Density 0.000%

    No Known Activations