© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13187
    Prev
    Next
    INDEX
    Explanations

    HTML or XML closing tags, especially `</data>`, `</delim>`, `</match>`, and `</read>`.

    oai_token-act-pair · gemini-2.0-flash

    HTML tag "</"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     framför
    -0.34
     tartalmaz
    -0.33
     animasi
    -0.32
    lasia
    -0.32
     कीजिए
    -0.32
     desp
    -0.32
     \
    -0.32
    angle
    -0.31
     =
    -0.30
     dibawah
    -0.30
    POSITIVE LOGITS
     party
    2.45
    party
    2.33
     Party
    2.33
    Party
    2.31
     parties
    2.30
     PARTY
    2.27
     Parties
    2.19
    PARTY
    2.17
    parties
    2.11
    Parties
    2.06
    Activations Density 1.294%

    No Known Activations