© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15035
    Prev
    Next
    INDEX
    Explanations

    the word "character" followed by words related to its traits

    oai_token-act-pair · gemini-2.0-flash

    terms related to character and characterization

    np_token-act-pair-logits · gpt-4o-mini

    character

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ærk
    -0.48
     em
    -0.48
    出版年
    -0.48
     estimés
    -0.47
    ofire
    -0.45
    aarrggbb
    -0.45
    раздо
    -0.45
    CPE
    -0.43
    MessageTagHelper
    -0.43
    ченко
    -0.43
    POSITIVE LOGITS
     kaynağından
    0.63
    TagMode
    0.62
     BoxDecoration
    0.62
    ResumeLayout
    0.59
     ExecuteAsync
    0.58
    Parcelize
    0.58
    csname
    0.57
    WithMany
    0.56
    الدراسه
    0.56
    RTDA
    0.56
    Activations Density 7.013%

    No Known Activations