© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213139
    Prev
    Next
    INDEX
    Explanations

    ev 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_5_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
    го
    0.94
     in
    0.88
    д
    0.86
    ~$
    0.84
    ५
    0.81
        
    0.81
    ไม่
    0.81
    ח
    0.79
    లో
    0.78
    이지만
    0.77
    POSITIVE LOGITS
    },
    1.27
    ير
    1.18
    n
    1.09
    ম
    1.03
    tte
    1.02
    niveau
    0.98
    mış
    0.97
     aprob
    0.97
    ing
    0.96
    ัน
    0.93
    Activations Density 0.001%

    No Known Activations