© 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. 1343
    Prev
    Next
    INDEX
    Explanations

    from/src/dest

    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
    到達
    0.49
    ायती
    0.44
    っしゃ
    0.43
    oyed
    0.42
    NameValuePair
    0.41
     ऐतिहासिक
    0.40
    ⒈
    0.40
     흘
    0.39
     সিংহ
    0.38
    ্ল্ড
    0.38
    POSITIVE LOGITS
     dire
    0.41
    dirs
    0.39
     dir
    0.39
     dirs
    0.36
     Dir
    0.35
     Dire
    0.34
     Consult
    0.34
    تور
    0.34
    Фа
    0.33
    如此
    0.33
    Activations Density 0.002%

    No Known Activations