© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45994
    Prev
    Next
    INDEX
    Explanations

    communication, transport, authority, disorders, infrastructure

    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_13_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
     I
    0.49
    ंकन
    0.47
    㑅
    0.46
     dagen
    0.45
     Vir
    0.45
     بودم
    0.45
     இங்கே
    0.44
     Baltimore
    0.44
     Vaill
    0.44
    教會
    0.44
    POSITIVE LOGITS
    4
    0.50
    ეს
    0.46
    ued
    0.46
    𝟰
    0.44
     pilotos
    0.43
    Naj
    0.42
    떳
    0.42
    Inicio
    0.41
    myst
    0.41
    Submission
    0.40
    Activations Density 0.016%

    No Known Activations