© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156751
    Prev
    Next
    INDEX
    Explanations

    sm or 's followed by punctuation or specific words

    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_2_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
    вання
    1.34
    ة
    1.21
    ки
    1.20
    ul
    1.18
    os
    1.17
    ia
    1.17
    した
    1.17
    an
    1.11
    ly
    1.11
    った
    1.09
    POSITIVE LOGITS
    x
    1.22
    DS
    1.16
     DS
    1.05
    ds
    1.04
     bodied
    1.02
    ’
    1.01
     ds
    0.98
     Políticas
    0.96
     Datas
    0.96
    你会
    0.94
    Activations Density 0.001%

    No Known Activations