© 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. 14969
    Prev
    Next
    INDEX
    Explanations

    HTML img tags and figure references with numbers

    oai_token-act-pair · gemini-2.0-flash

    HTML and numerical elements

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

    image file code

    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
    tvguidetime
    -0.94
    enterOuterAlt
    -0.88
     AssemblyCulture
    -0.87
    PerformLayout
    -0.85
    CppMethod
    -0.79
    SharedDtor
    -0.77
    IntoConstraints
    -0.77
    +#+#
    -0.77
    mybatisplus
    -0.75
     Roskov
    -0.74
    POSITIVE LOGITS
    </strong>
    0.52
    !
    0.48
    8
    0.48
    0
    0.46
    caya
    0.46
    -
    0.45
     Maggiore
    0.43
    様に
    0.42
    おきます
    0.41
    9
    0.41
    Activations Density 6.772%

    No Known Activations