© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198875
    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_50_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
    Ꮅ
    0.40
    ക്കം
    0.39
    ಬ್ಬ
    0.38
     dur
    0.38
    丂
    0.37
     LY
    0.37
    روں
    0.37
     OSError
    0.37
     brew
    0.36
     Spin
    0.36
    POSITIVE LOGITS
    stin
    0.43
    Herald
    0.40
    桓
    0.40
    ፫
    0.40
    Uid
    0.39
    stad
    0.38
    guardian
    0.38
     UID
    0.38
    kran
    0.38
     cang
    0.37
    Activations Density 0.000%

    No Known Activations