© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 78587
    Prev
    Next
    INDEX
    Explanations

    always

    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_29_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
    চ
    0.32
     původ
    0.32
     indictment
    0.32
    跟着
    0.32
    등
    0.32
    即便
    0.31
    等
    0.31
     fulfilment
    0.31
    inf
    0.30
     등
    0.30
    POSITIVE LOGITS
     always
    0.45
     siempre
    0.44
     πάντα
    0.43
     ಯಾವಾಗ
    0.42
     zawsze
    0.40
     Siempre
    0.40
     всегда
    0.39
    always
    0.39
     sempre
    0.38
     Always
    0.38
    Activations Density 0.013%

    No Known Activations