© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64280
    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_41_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
     Lawrence
    0.39
     GUAR
    0.38
     entail
    0.37
    bore
    0.37
     Bore
    0.35
    ৌশ
    0.35
     Nuremberg
    0.35
    ጻ
    0.35
     adversarial
    0.34
     SHER
    0.34
    POSITIVE LOGITS
    менти
    0.43
    பாடு
    0.41
    Sur
    0.40
    UJ
    0.40
    Gl
    0.38
    籾
    0.38
    Alle
    0.37
    plants
    0.36
    скет
    0.36
    Exper
    0.36
    Activations Density 0.000%

    No Known Activations