© 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. 201445
    Prev
    Next
    INDEX
    Explanations

    assassination, Unification Church, Article 9

    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
     बढ़े
    0.18
    ॉप
    0.17
    vived
    0.17
     深
    0.17
     १५
    0.17
    ကြည်
    0.17
    ॉर
    0.17
    𝐌
    0.17
    ရောက်
    0.17
    鏄
    0.17
    POSITIVE LOGITS
    <0x0D>
    0.17
    eto
    0.17
    <start_of_image>
    0.17
    ely
    0.17
    '
    0.16
    }
    0.16
    ↵↵↵
    0.15
     Harlem
    0.15
     DE
    0.15
    etti
    0.15
    Activations Density 0.001%

    No Known Activations