© 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. 14015
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or symbols including units and measurements

    oai_token-act-pair · gemini-2.0-flash

    $

    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
     River
    -0.54
     N
    -0.52
    ®
    -0.51
     driver
    -0.51
    argout
    -0.50
    ☐
    -0.49
     Str
    -0.49
     II
    -0.49
    raya
    -0.49
    vertret
    -0.49
    POSITIVE LOGITS
     समीक्षाओं
    0.78
    Personendaten
    0.77
     snippetHide
    0.74
    Datuak
    0.73
     CreateTagHelper
    0.70
     initComponents
    0.69
    PerformLayout
    0.68
    verifyException
    0.67
    AddTagHelper
    0.67
     tartalomajánló
    0.66
    Activations Density 1.416%

    No Known Activations