© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35542
    Prev
    Next
    INDEX
    Explanations

    Tar / Tare

    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_50_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
     eng
    0.49
     Eng
    0.42
    eng
    0.42
    土
    0.41
    영
    0.40
     Pfl
    0.39
     انج
    0.37
    奥
    0.37
     CAL
    0.37
     현
    0.37
    POSITIVE LOGITS
    Tara
    0.63
     Tara
    0.61
     Tare
    0.61
     Tar
    0.60
     Ts
    0.57
     Tang
    0.56
     Tag
    0.54
    Tar
    0.53
     tare
    0.52
     唐
    0.52
    Activations Density 0.033%

    No Known Activations