© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214576
    Prev
    Next
    INDEX
    Explanations

    graveyards / gravediggers / gravy

    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_5_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
    .
    1.59
    ل
    1.30
    I
    1.26
    1.17
    u
    1.17
    at
    1.05
     analys
    1.03
    ó
    0.96
    ق
    0.95
    פ
    0.94
    POSITIVE LOGITS
    ди
    1.26
    ні
    1.25
    de
    1.08
    CC
    1.04
    carotene
    1.04
    ция
    1.03
    sustainable
    1.03
    tc
    1.02
    transformation
    1.01
    destroyed
    1.00
    Activations Density 0.000%

    No Known Activations