© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16042
    Prev
    Next
    INDEX
    Explanations

    gene sequences and DNA

    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_34_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
     facilitation
    0.44
    dmn
    0.41
     Facilit
    0.40
     Assess
    0.39
     Ministerio
    0.39
    Assess
    0.38
    facilit
    0.38
    용
    0.38
    ائية
    0.37
     Taunton
    0.37
    POSITIVE LOGITS
     sequences
    0.44
     invers
    0.40
     пас
    0.38
    这段
    0.36
    死去
    0.36
     구간
    0.36
     Sequences
    0.36
     haircuts
    0.35
    ETC
    0.35
    癒
    0.35
    Activations Density 0.015%

    No Known Activations