© 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. 2822
    Prev
    Next
    INDEX
    Explanations

    book publishing information

    oai_token-act-pair · gemini-2.0-flash

    formatting and publication structures

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

    punctuation

    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
    سطس
    -0.60
    StructEnd
    -0.48
    InitVars
    -0.48
    NameInMap
    -0.47
     naturales
    -0.45
    干
    -0.44
    writeField
    -0.44
    }:${
    -0.43
     >=",
    -0.43
     via
    -0.43
    POSITIVE LOGITS
    DockStyle
    0.68
    #+#
    0.62
    \{\\
    0.61
    出版年
    0.60
    -------
    0.52
     tabPage
    0.52
    ंदीखरीदारी
    0.52
    lessly
    0.52
     Sorbonne
    0.51
    __":
    0.51
    Activations Density 0.431%

    No Known Activations