© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 11907
    Prev
    Next
    INDEX
    Explanations

    punctuation and common words used in making contradictions or disagreements

    oai_token-act-pair · gemini-2.0-flash

    punctuation and "of"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    évaluateur
    -0.67
    Rohy
    -0.65
    ſelves
    -0.63
    lgari
    -0.61
     pinulongan
    -0.59
    Demografía
    -0.56
    ScopeManager
    -0.55
    yntaxException
    -0.54
    يكب
    -0.54
     endwhile
    -0.54
    POSITIVE LOGITS
     of
    2.70
    of
    1.52
     Of
    1.47
    Of
    1.38
     của
    1.23
    ของ
    1.11
     OF
    1.06
    tof
    1.01
     ofc
    0.95
     ofthe
    0.86
    Activations Density 4.570%

    No Known Activations