© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43100
    Prev
    Next
    INDEX
    Explanations

    5' and 3' ends or termini

    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_22_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
     Phy
    0.46
     Utilization
    0.42
    <b>
    0.41
     candles
    0.41
     denom
    0.40
     Germania
    0.40
     &
    0.39
     ailleurs
    0.39
     fakat
    0.39
     utilization
    0.39
    POSITIVE LOGITS
    akra
    0.49
    StubCompat
    0.49
    ดับ
    0.45
    濕
    0.45
     मंगलवार
    0.44
    Producto
    0.42
    ẋ
    0.41
    apag
    0.40
    ۳
    0.40
    👹
    0.40
    Activations Density 0.001%

    No Known Activations