© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207944
    Prev
    Next
    INDEX
    Explanations

    double quote

    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_56_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
     Ф
    0.45
     c
    0.44
    ෆ
    0.42
    法人
    0.42
    ക്
    0.41
    ഫോ
    0.40
     f
    0.40
    িয়াস
    0.40
     കോണ്‍
    0.38
     Finger
    0.38
    POSITIVE LOGITS
     pr
    0.42
     логи
    0.42
    pr
    0.42
     log
    0.41
    Pr
    0.40
    LOG
    0.39
    amping
    0.39
     Pr
    0.38
    ilog
    0.38
    庀
    0.37
    Activations Density 0.000%

    No Known Activations