© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197666
    Prev
    Next
    INDEX
    Explanations

    Sagarmatha Chomolungma

    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_4_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
    ة
    1.05
    د
    1.04
    ד
    0.91
    リ
    0.89
    টি
    0.89
    nél
    0.88
    ن
    0.79
    ும்
    0.77
    ception
    0.76
    ロ
    0.76
    POSITIVE LOGITS
     (
    1.16
     to
    1.02
    dır
    1.02
     can
    0.99
    то
    0.97
    to
    0.94
    สามารถ
    0.94
     kunna
    0.93
     could
    0.91
     poderá
    0.91
    Activations Density 0.000%

    No Known Activations