© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 237852
    Prev
    Next
    INDEX
    Explanations

    resignation

    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
     रिक्वायरमेंट
    0.38
    omania
    0.37
    écou
    0.37
    paragraphs
    0.37
    getSave
    0.36
    転
    0.35
     灬
    0.35
    Geometric
    0.35
    रेन्द्र
    0.35
     సంవ
    0.35
    POSITIVE LOGITS
     basa
    0.40
     Tus
    0.38
    ib
    0.38
     bec
    0.38
     considering
    0.38
     NSA
    0.38
    ñada
    0.38
     dati
    0.38
     withd
    0.38
    다
    0.38
    Activations Density 0.000%

    No Known Activations