© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230175
    Prev
    Next
    INDEX
    Explanations

    grounded

    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
    و
    1.81
    ด
    1.80
    م
    1.76
    ي
    1.76
    ت
    1.66
    т
    1.58
    ল
    1.53
    로
    1.47
    м
    1.38
    К
    1.37
    POSITIVE LOGITS
    fi
    0.99
    fly
    0.96
    ris
    0.94
     n
    0.92
     y
    0.91
    ra
    0.90
    arı
    0.89
     (
    0.89
    ’
    0.89
    fü
    0.88
    Activations Density 0.000%

    No Known Activations