© 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. 11587
    Prev
    Next
    INDEX
    Explanations

    parts of HTML code defining the name and description of fields and datatypes, particularly when listing deprecated items

    oai_token-act-pair · gemini-2.0-flash

    code/markup language

    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
     Roskov
    -0.85
     contextLoads
    -0.64
     للاسماء
    -0.63
     $>$
    -0.62
     exceeding
    -0.60
    <?
    -0.58
     exceed
    -0.58
     meaning
    -0.57
    PyExc
    -0.56
    TypedDataSet
    -0.55
    POSITIVE LOGITS
     بيها
    0.53
    Portály
    0.49
    AutoScale
    0.49
    "…
    0.47
    ContentAsync
    0.47
    ActionResult
    0.46
    withIdentifier
    0.43
    ‘’
    0.43
    ResumeLayout
    0.43
    Inbound
    0.42
    Activations Density 1.310%

    No Known Activations