© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 150882
    Prev
    Next
    INDEX
    Explanations

    ard

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     head
    0.44
     Head
    0.41
     उत्तर
    0.38
     UL
    0.38
    दात
    0.37
     embl
    0.36
     kepala
    0.36
    砓
    0.36
     Reaction
    0.36
     Heading
    0.36
    POSITIVE LOGITS
    rup
    0.68
    rub
    0.67
    rum
    0.64
    rus
    0.62
    rol
    0.59
    russ
    0.58
    romy
    0.57
    ruck
    0.57
    rut
    0.57
    rust
    0.56
    Activations Density 0.000%

    No Known Activations