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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165207
    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_13_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
    Packed
    0.49
    ولت
    0.49
    heti
    0.47
    埃
    0.46
    Signature
    0.45
    фер
    0.45
    rui
    0.45
    abei
    0.45
    für
    0.45
    طار
    0.45
    POSITIVE LOGITS
     toler
    0.55
     pedest
    0.51
     boxes
    0.50
     ],
    0.50
     cough
    0.49
     bandit
    0.49
     stenosis
    0.49
     hopelessness
    0.48
     hand
    0.48
     persuas
    0.48
    Activations Density 0.000%

    No Known Activations