© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199031
    Prev
    Next
    INDEX
    Explanations

    deceased person, mournful, dog, unidentified, CORRECTION

    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_27_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
     باقی
    0.41
     Danach
    0.41
    ätzen
    0.39
    甠
    0.38
     arma
    0.37
     webhook
    0.37
     canciones
    0.36
     Scalar
    0.36
    arma
    0.36
    ână
    0.35
    POSITIVE LOGITS
     crouching
    0.38
    浚
    0.35
     divers
    0.35
    May
    0.35
     counterpart
    0.34
     decide
    0.34
    Kur
    0.34
     MBC
    0.33
     invest
    0.33
     ir
    0.33
    Activations Density 0.001%

    No Known Activations