© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164925
    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_31_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
     Poo
    0.39
    '][$
    0.39
    ambuk
    0.38
     confirme
    0.37
     Flore
    0.36
     holl
    0.36
     Bete
    0.35
    꾿
    0.34
    Flore
    0.34
    されて
    0.33
    POSITIVE LOGITS
     pressing
    0.40
    BackPressed
    0.39
    வங்க
    0.38
     interdependent
    0.38
    icies
    0.38
    ignent
    0.37
    Scalar
    0.37
    scalar
    0.37
     Agreements
    0.37
     Scalar
    0.37
    Activations Density 0.000%

    No Known Activations