© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 243262
    Prev
    Next
    INDEX
    Explanations

    briefly describe

    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_40_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
     slipping
    0.42
     технологі
    0.42
     historical
    0.39
     telehealth
    0.39
    粗
    0.39
    isek
    0.38
    뭡
    0.38
     historically
    0.38
    Historical
    0.38
     rustic
    0.37
    POSITIVE LOGITS
     언급
    0.47
    сите
    0.44
     Mention
    0.44
     mention
    0.43
    をご紹介
    0.41
    ご紹介
    0.41
     demonstra
    0.40
    skich
    0.38
    聿
    0.38
    を紹介
    0.38
    Activations Density 0.008%

    No Known Activations