© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165621
    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
    leti
    0.42
    ুট
    0.40
    馈
    0.39
     alphan
    0.38
    უტ
    0.38
    achos
    0.38
     amplifier
    0.37
     appropri
    0.37
    hu
    0.37
    വ്വ
    0.36
    POSITIVE LOGITS
    Created
    0.40
    CreationFailed
    0.36
    **(
    0.36
     لکھا
    0.35
    KX
    0.35
    ("{
    0.35
    महिलाओं
    0.35
     Created
    0.35
     положение
    0.35
     Written
    0.34
    Activations Density 0.000%

    No Known Activations