© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62452
    Prev
    Next
    INDEX
    Explanations

    dirty

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     dirty
    1.27
     Dirty
    1.23
    Dirty
    1.17
    dirty
    1.01
    骯
    0.60
    脏
    0.58
    肮
    0.45
    髒
    0.44
     ട
    0.40
     Cummins
    0.40
    POSITIVE LOGITS
     telemetry
    1.78
     Teller
    1.74
     tela
    1.71
     Tela
    1.68
    Telemetry
    1.62
    tela
    1.51
    Teller
    1.51
     teller
    1.50
     Telf
    1.50
    Tela
    1.48
    Activations Density 0.007%

    No Known Activations