© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180750
    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_24_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
    к
    0.55
    िक
    0.54
    ن
    0.53
    ک
    0.53
    клю
    0.52
    ק
    0.51
    на
    0.50
    א
    0.50
    ल
    0.49
    ни
    0.48
    POSITIVE LOGITS
    Univ
    0.43
    गित
    0.42
    posed
    0.42
    ora
    0.41
    umas
    0.41
    anov
    0.40
    ataya
    0.40
     对象
    0.40
     বিত
    0.39
     打
    0.39
    Activations Density 0.000%

    No Known Activations