© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203344
    Prev
    Next
    INDEX
    Explanations

    worker rights and contracts

    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_12_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
     unsatisfactory
    0.34
     untenable
    0.34
    ERA
    0.33
    VU
    0.33
    lama
    0.32
    Ö
    0.32
    三个
    0.31
     здра
    0.30
     disapp
    0.30
     offend
    0.30
    POSITIVE LOGITS
    icos
    0.36
     웹
    0.33
     वेट
    0.32
     Countdown
    0.31
     परिवहन
    0.31
    融
    0.30
     कंग
    0.29
     Kf
    0.29
    ẩy
    0.29
     टार
    0.29
    Activations Density 0.000%

    No Known Activations