© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206370
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
    ';
    0.50
    wesen
    0.50
    slategray
    0.46
     admon
    0.46
    ophilus
    0.46
    pengaruhi
    0.46
    og
    0.45
     reve
    0.45
    phrase
    0.45
    ./
    0.44
    POSITIVE LOGITS
     contatt
    0.48
     geometría
    0.45
    粿
    0.45
     आत्मनिर्भर
    0.43
     plástico
    0.43
    АР
    0.43
    ไซ
    0.43
    共和国
    0.42
     usuários
    0.42
     República
    0.42
    Activations Density 0.000%

    No Known Activations