© 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
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10931
    Prev
    Next
    INDEX
    Explanations

    the word "factor"

    oai_token-act-pair · gemini-2.0-flash

    factor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     factor
    -2.73
    factor
    -2.42
     factors
    -2.33
     Factor
    -2.30
    Factor
    -2.19
    factors
    -2.17
     Factors
    -2.11
     FACTOR
    -2.02
    Factors
    -1.95
     FACTORS
    -1.84
    POSITIVE LOGITS
    出版年
    0.77
     الرياضيه
    0.76
     snippetHide
    0.75
     pleaſure
    0.72
     GenerationType
    0.70
    <_>
    0.70
    \{\\
    0.68
     GIPHY
    0.67
     fevere
    0.66
     poffible
    0.66
    Activations Density 0.718%

    No Known Activations