© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53255
    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
    乆
    0.32
    WhiteSpace
    0.29
     மதி
    0.29
    grimas
    0.28
    分數
    0.28
    វា
    0.27
     філь
    0.27
    telefone
    0.27
    spielen
    0.27
    Jimbo
    0.27
    POSITIVE LOGITS
     noticeable
    0.31
    亵
    0.30
     बांग
    0.30
     mainly
    0.30
     cloning
    0.29
     digs
    0.29
     catchy
    0.29
     dig
    0.29
     digoxin
    0.28
     Dig
    0.28
    Activations Density 0.000%

    No Known Activations