© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7090
    Prev
    Next
    INDEX
    Explanations

    articles and words that suggest leadership or governance

    oai_token-act-pair · gemini-2.0-flash

    OGND

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ownership
    -0.74
     Ownership
    -0.73
    ownership
    -0.66
    Ownership
    -0.62
    seats
    -0.58
     LEADERSHIP
    -0.57
     possesso
    -0.56
    seat
    -0.55
     leadership
    -0.54
     possession
    -0.54
    POSITIVE LOGITS
    OGND
    0.73
    PerformLayout
    0.68
    RenderAtEndOf
    0.68
    دانشنامهٔ
    0.67
     يتيمه
    0.60
     ")");
    0.58
     nahilalakip
    0.56
    SourceChecksum
    0.54
     eletrônico
    0.54
    بوابة
    0.54
    Activations Density 3.420%

    No Known Activations