© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130001
    Prev
    Next
    INDEX
    Explanations

    illierte able

    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_6_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
    ம்
    1.04
    У
    0.89
    आई
    0.88
    ே
    0.88
     realizará
    0.86
     cuyas
    0.86
     deficient
    0.86
     reconoc
    0.85
     provocar
    0.85
     déplacer
    0.85
    POSITIVE LOGITS
    to
    1.18
    sp
    1.14
    j
    1.12
    sh
    1.09
    sc
    1.08
    tr
    1.05
    ld
    0.99
    com
    0.99
    sk
    0.97
    ss
    0.97
    Activations Density 0.000%

    No Known Activations