© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229005
    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_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
    ي
    1.38
     at
    1.31
     as
    1.27
     for
    1.20
     with
    1.19
    d
    1.15
    ר
    1.15
    י
    1.13
    ő
    1.13
    پ
    1.10
    POSITIVE LOGITS
    om
    0.88
    кович
    0.84
    isas
    0.84
    icans
    0.83
    bilir
    0.82
    ciaux
    0.82
    theon
    0.82
    grim
    0.81
    nen
    0.81
    bein
    0.81
    Activations Density 0.000%

    No Known Activations