© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82917
    Prev
    Next
    INDEX
    Explanations

    structural elements

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
     D
    0.53
    D
    0.47
     الد
    0.45
    Michael
    0.41
     Ashraf
    0.40
    roof
    0.39
    yong
    0.39
    DATA
    0.38
    竈
    0.38
    iD
    0.38
    POSITIVE LOGITS
    రే
    0.40
     Hour
    0.40
     workstation
    0.36
    จอ
    0.35
     秦
    0.35
    ኝ
    0.35
    竟
    0.35
     腰
    0.34
    érist
    0.34
     फाइन
    0.34
    Activations Density 0.002%

    No Known Activations