© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3613
    Prev
    Next
    INDEX
    Explanations

    statistical text, especially about percentages or comparisons between groups

    oai_token-act-pair · gemini-2.0-flash

    scientific context with percentages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     musically
    -1.12
     financially
    -1.07
     Regarding
    -1.02
     regarding
    -0.97
    Regarding
    -0.94
    regarding
    -0.94
     quantitatively
    -0.94
     offensively
    -0.93
     psychologically
    -0.92
     Physically
    -0.91
    POSITIVE LOGITS
    providedIn
    0.67
     propOrder
    0.59
    Biographie
    0.49
     fä
    0.46
     لينك
    0.46
    diac
    0.46
    zeugt
    0.45
    adaptiveStyles
    0.45
     &___
    0.43
    Etimología
    0.43
    Activations Density 1.209%

    No Known Activations