© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 243820
    Prev
    Next
    INDEX
    Explanations

    loss, reserve, estimated

    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_40_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
     write
    2.67
     Write
    2.42
    write
    2.38
    Write
    2.31
    寫
    2.17
    写
    2.16
     writing
    2.11
     WRITE
    2.11
     escribir
    2.08
     kirjo
    2.08
    POSITIVE LOGITS
     Quadro
    0.35
    भेद
    0.35
    idlo
    0.34
    Stanley
    0.34
     Kuro
    0.33
    iziert
    0.33
    yak
    0.32
     Stanley
    0.32
    栤
    0.32
    ູ້
    0.32
    Activations Density 0.008%

    No Known Activations