© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43448
    Prev
    Next
    INDEX
    Explanations

    wakes up with no memory

    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_22_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
     كلهم
    0.43
     включают
    0.42
    lük
    0.37
    격
    0.37
    酶
    0.36
    Seminar
    0.36
     이해
    0.36
     стоят
    0.36
     ऑल
    0.36
    लभ
    0.36
    POSITIVE LOGITS
    ipay
    0.42
    麪
    0.41
    oned
    0.40
     eğer
    0.39
    पहरण
    0.39
     উদ্বাস্ত
    0.39
     plastique
    0.39
     sincerely
    0.39
     ransomware
    0.39
    傥
    0.38
    Activations Density 0.015%

    No Known Activations