© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 808
    Prev
    Next
    INDEX
    Explanations

    capitalized words (often proper nouns) and parts of URLs and mathematical formulas

    oai_token-act-pair · gemini-2.0-flash

    Citations and character strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    Дереккөздер
    -0.48
     kuat
    -0.46
    一
    -0.43
     Otherwise
    -0.42
    الدراسه
    -0.42
     arred
    -0.40
    Possibility
    -0.40
     connues
    -0.40
     cercano
    -0.39
     ход
    -0.38
    POSITIVE LOGITS
    出版年
    0.84
    bootstrapcdn
    0.72
    \{\\
    0.72
    ]")]
    0.70
    rawDesc
    0.68
    EndInit
    0.65
     fieldNum
    0.65
     kasarigan
    0.63
     MainAxisSize
    0.63
     Signalez
    0.62
    Activations Density 15.362%

    No Known Activations