© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2164
    Prev
    Next
    INDEX
    Explanations

    code termination

    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_39_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
    անք
    0.20
     एजुकेशन
    0.20
     सेकेंडरी
    0.20
    涣
    0.19
     अय्यर
    0.19
     اخذت
    0.19
    كز
    0.19
     drawers
    0.19
    オレンジ
    0.18
     Maraton
    0.18
    POSITIVE LOGITS
     hub
    0.21
     manufactured
    0.20
    cropping
    0.20
    cin
    0.19
    錆
    0.19
     umat
    0.19
    issants
    0.19
    zing
    0.18
     versa
    0.18
     successivo
    0.18
    Activations Density 0.099%

    No Known Activations