© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76117
    Prev
    Next
    INDEX
    Explanations

    **numbers and symbols within text descriptions**

    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_31_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
    dds
    0.38
    plex
    0.38
    strings
    0.35
     interrog
    0.35
    ("_
    0.35
    pdb
    0.35
    ഞ്ചി
    0.35
     capacitance
    0.33
    board
    0.33
     polystyrene
    0.33
    POSITIVE LOGITS
    峣
    0.41
    峈
    0.40
    ಖ
    0.39
     도
    0.39
     Marino
    0.39
     DISCOUNT
    0.39
    STIT
    0.38
    చన
    0.38
     mussten
    0.38
    ก็ได้
    0.38
    Activations Density 0.002%

    No Known Activations