© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32650
    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_40_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
    ᆻ
    0.43
     തന്നെ
    0.38
     വയ
    0.38
     geworden
    0.37
    ोगी
    0.37
     किए
    0.36
    hsl
    0.36
     randomize
    0.36
     PSI
    0.36
     peta
    0.36
    POSITIVE LOGITS
    は
    1.01
    은
    0.88
    는
    0.84
     là
    0.82
    是
    0.82
     adalah
    0.77
    は見
    0.71
     は
    0.71
    はお
    0.71
     är
    0.67
    Activations Density 0.002%

    No Known Activations