© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218505
    Prev
    Next
    INDEX
    Explanations

    spectacular views from

    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_31_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
    Bk
    0.37
    ឿ
    0.35
     disent
    0.35
     Kurz
    0.35
     المقام
    0.34
    easeInOut
    0.34
    fillText
    0.34
     Kiz
    0.34
    崎
    0.34
    reporting
    0.33
    POSITIVE LOGITS
     bee
    0.43
    மின்றி
    0.40
     AAC
    0.39
     Local
    0.39
     तुलसी
    0.38
    筋肉
    0.37
     bowel
    0.36
     urging
    0.36
    蜂
    0.36
     follicle
    0.36
    Activations Density 0.001%

    No Known Activations