© 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
    2. Gemma-2-2B
    3. 23-GEMMASCOPE-TRANSCODER-16K
    4. 12656
    Prev
    Next
    INDEX
    Explanations

    strings of characters representing lists and tables of data including section breaks

    oai_token-act-pair · gemini-2.0-flash

    Complex text with numbers

    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
    $\
    -1.08
    (
    -1.05
    <b>
    -1.01
    “
    -0.99
    <strong>
    -0.99
    $
    -0.99
    <code>
    -0.98
    [
    -0.97
    ((
    -0.96
    <i>
    -0.95
    POSITIVE LOGITS
    __":
    
    1.43
    __':
    
    1.35
     $_"
    1.34
    ^(@)
    1.32
    OGND
    1.30
    >\<^
    1.22
    NUMX
    1.20
    tagHelperRunner
    1.20
     صوتيه
    1.20
     */;
    1.16
    Activations Density 8.137%

    No Known Activations