© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11323
    Prev
    Next
    INDEX
    Explanations

    html formatting tags and the content between them

    oai_token-act-pair · gemini-2.0-flash

    Code and logs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     <
    -2.20
     >
    -1.82
     $<
    -1.54
    }<
    -1.50
    )<
    -1.45
    }>
    -1.43
     $<$
    -1.41
    $<
    -1.40
    ]>
    -1.40
     (<
    -1.38
    POSITIVE LOGITS
    apimachinery
    0.65
    DataAnnotations
    0.65
     nahilalakip
    0.63
    contentLoaded
    0.62
    dafx
    0.61
    ########.
    0.60
     NSCoder
    0.60
    MeasureSpec
    0.59
    MigrationBuilder
    0.59
     المعيارى
    0.58
    Activations Density 3.338%

    No Known Activations