© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215998
    Prev
    Next
    INDEX
    Explanations

    more deterministic, focused, predictable

    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_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
     partition
    0.35
     partitions
    0.34
    seem
    0.33
    partitions
    0.32
    amplitude
    0.32
     sphere
    0.32
     `>`,
    0.32
    吿
    0.32
    sphere
    0.31
    boleh
    0.31
    POSITIVE LOGITS
     inutil
    0.39
    ייס
    0.38
    mergeddata
    0.37
     청바
    0.37
    edi
    0.36
    Sums
    0.36
     高校
    0.36
     tecido
    0.35
     جین
    0.35
     magist
    0.35
    Activations Density 0.011%

    No Known Activations