© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 490
    Prev
    Next
    INDEX
    Explanations

    merchandise

    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_44_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     الهدف
    0.40
    亽
    0.38
     Belong
    0.37
    सन
    0.37
    Loads
    0.37
     संसाधन
    0.36
    setter
    0.36
     Executes
    0.35
     ઉપયોગ
    0.34
    水平
    0.34
    POSITIVE LOGITS
    chend
    0.54
    ཆ
    0.44
    ufact
    0.43
     mannitol
    0.42
    che
    0.42
     Shall
    0.41
    chest
    0.40
    ket
    0.40
    shall
    0.39
    iched
    0.39
    Activations Density 0.036%

    No Known Activations