© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29881
    Prev
    Next
    INDEX
    Explanations

    ethical statement or consideration

    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
    Vector
    0.46
     Vector
    0.42
     vectorial
    0.40
    向量
    0.39
    
    0.38
    ベクトル
    0.38
     벡터
    0.37
    ᠬ
    0.37
     наде
    0.37
    唋
    0.36
    POSITIVE LOGITS
     confirms
    0.51
     Confirmation
    0.48
    confirm
    0.48
     confirming
    0.48
     confirmation
    0.46
     declaration
    0.45
    declaration
    0.45
     confirm
    0.45
     Confirm
    0.44
     mutable
    0.42
    Activations Density 0.002%

    No Known Activations