© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 203560
    Prev
    Next
    INDEX
    Explanations

    access key

    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_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
    äd
    0.35
     blow
    0.35
     стара
    0.35
    偶尔
    0.33
     יד
    0.33
    腌
    0.33
    一时
    0.33
     Apakah
    0.33
     try
    0.32
     apakah
    0.32
    POSITIVE LOGITS
     এরপর
    0.43
     Layton
    0.43
    এরপর
    0.38
     சென்ற
    0.38
     இவற்ற
    0.36
     ישראל
    0.36
    ⿱
    0.36
    ্নে
    0.36
    orphous
    0.35
    ENTY
    0.35
    Activations Density 0.000%

    No Known Activations