© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11612
    Prev
    Next
    INDEX
    Explanations

    small words and markers, and some foreign words/characters

    oai_token-act-pair · gemini-2.0-flash

    Academic, technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     con
    -0.58
     un
    -0.53
     de
    -0.51
     en
    -0.50
     (
    -0.49
     re
    -0.48
     H
    -0.47
     <
    -0.47
     the
    -0.47
     di
    -0.45
    POSITIVE LOGITS
    RegressionTest
    1.10
     doubtnut
    1.04
    NUMX
    0.97
    oredCriteria
    0.95
     kaarangay
    0.91
     Houſe
    0.88
    انيف
    0.87
    contentLoaded
    0.85
    ^(@)
    0.84
    ########.
    0.83
    Activations Density 3.265%

    No Known Activations