© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 197060
    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_27_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
     ঈ
    0.38
     স্বল্প
    0.37
    殯
    0.37
    Training
    0.34
     ISPs
    0.34
     intercom
    0.34
     SBOM
    0.34
    EIN
    0.34
     scripts
    0.33
    ]_
    0.33
    POSITIVE LOGITS
    கால
    0.39
    velle
    0.38
    परेट
    0.38
    mented
    0.37
     അമേരിക്ക
    0.37
    itioner
    0.37
    riminating
    0.37
    ಲಿಯ
    0.36
    chnik
    0.36
    ندہ
    0.36
    Activations Density 0.000%

    No Known Activations