© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60945
    Prev
    Next
    INDEX
    Explanations

    passing by each other

    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
    ة
    1.01
    ı
    0.97
    d
    0.96
    was
    0.93
    it
    0.92
     was
    0.89
    ,
    0.87
    な
    0.87
    with
    0.83
    t
    0.82
    POSITIVE LOGITS
     or
    1.17
    어가
    0.91
     on
    0.85
     at
    0.82
    ↵
    0.79
    ור
    0.78
    나
    0.75
    더
    0.74
    জ
    0.73
    ку
    0.72
    Activations Density 0.000%

    No Known Activations