© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53896
    Prev
    Next
    INDEX
    Explanations

    recursive data structures or tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_30_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
    บาท
    0.32
     Busch
    0.31
    敝
    0.29
     России
    0.29
    ১১
    0.29
    Rather
    0.28
     ಕ್ಯಾ
    0.28
     Rather
    0.28
    পুরের
    0.28
    rather
    0.28
    POSITIVE LOGITS
     {},
    0.36
     lived
    0.31
    }},
    0.29
     [],
    0.29
     Ver
    0.29
    "",
    0.28
    ...,
    0.28
     amend
    0.28
    AMOS
    0.27
     {}",
    0.27
    Activations Density 0.003%

    No Known Activations