© 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
    2. Gemma-3-27B-IT
    3. 29-GEMMASCOPE-2-TRANSCODER-262K
    4. 181008
    Prev
    Next
    INDEX
    Explanations

    foundation event

    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_29_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
    şam
    0.39
    ğrafl
    0.38
     அவை
    0.37
    ácil
    0.37
    ٛ
    0.37
    ૬
    0.37
     superstructure
    0.36
    に対し
    0.36
    ப்பில்
    0.35
    家用
    0.35
    POSITIVE LOGITS
    TAINS
    0.37
     konflik
    0.37
     suara
    0.36
     persecution
    0.35
    แท
    0.35
     neglected
    0.34
     femin
    0.34
     feminism
    0.34
    いない
    0.34
    ))^
    0.33
    Activations Density 0.000%

    No Known Activations