© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201527
    Prev
    Next
    INDEX
    Explanations

    confirmation bias

    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_12_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
     Herbst
    0.42
    IS
    0.39
    성이
    0.39
    气
    0.39
    汉
    0.38
    P
    0.38
     heran
    0.37
    병
    0.37
     tất
    0.37
     nằm
    0.36
    POSITIVE LOGITS
     )-
    0.46
    )」
    0.45
    )。
    0.44
     비교
    0.42
    ]。
    0.42
    。.
    0.41
     [])
    0.41
     receptacles
    0.41
    )").
    0.40
     আপনাকে
    0.40
    Activations Density 0.000%

    No Known Activations