© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232799
    Prev
    Next
    INDEX
    Explanations

    HSBC and NBC News

    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_6_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
    0.84
    ine
    0.84
    le
    0.82
    c
    0.80
    itet
    0.79
    ↵
    0.77
    ing
    0.75
    arı
    0.74
    ,
    0.73
    로
    0.73
    POSITIVE LOGITS
    ０
    0.98
     givenChar
    0.96
    ）；
    0.89
    PPh
    0.85
     pdelay
    0.83
     dajj
    0.83
    ン
    0.81
    yanka
    0.80
     attham
    0.79
    ONEDB
    0.79
    Activations Density 0.000%

    No Known Activations