© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10404
    Prev
    Next
    INDEX
    Explanations

    words that end in consonants and are followed by function words or punctuation

    oai_token-act-pair · gemini-2.0-flash

    determination

    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
    
    -0.87
    enumi
    -0.76
    AxisAlignment
    -0.71
    حوالہ
    -0.67
    ंदीखरीदारी
    -0.58
     pinulongan
    -0.56
    findpost
    -0.56
     hopes
    -0.56
    最快更新
    -0.55
     NSCoder
    -0.55
    POSITIVE LOGITS
     determined
    2.33
     determination
    2.11
    determined
    2.02
     Determined
    1.91
    determination
    1.81
     Determination
    1.80
    Determination
    1.69
     détermination
    1.64
     déterminé
    1.63
     determinación
    1.57
    Activations Density 4.741%

    No Known Activations