© 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. 53170
    Prev
    Next
    INDEX
    Explanations

    synthetic biology and genome engineering

    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
     foundations
    0.42
    绺
    0.40
     treatments
    0.37
     including
    0.37
     Motorola
    0.37
     Majorana
    0.37
     attic
    0.36
     Foundations
    0.36
    淄
    0.36
     IT
    0.36
    POSITIVE LOGITS
    ưở
    0.37
    irit
    0.37
    镳
    0.36
     bæ
    0.36
    funct
    0.35
    Փ
    0.35
    Payout
    0.35
     Brookfield
    0.35
    returnData
    0.34
    clearInterval
    0.34
    Activations Density 0.033%

    No Known Activations