© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15090
    Prev
    Next
    INDEX
    Explanations

    phrases where someone is quoted as saying something

    oai_token-act-pair · gemini-2.0-flash

    said

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     defaultstate
    -0.61
     '\\;'
    -0.53
    øya
    -0.52
    PositiveButton
    -0.51
    новништво
    -0.50
     faid
    -0.49
    photobucket
    -0.49
    parametrize
    -0.48
    RTLR
    -0.47
    rxjs
    -0.46
    POSITIVE LOGITS
     betweenstory
    0.52
     kiệm
    0.51
     overloading
    0.50
    ướt
    0.50
     sclero
    0.50
    沿革
    0.49
     fatale
    0.49
     fotogra
    0.49
    ueux
    0.47
     Amber
    0.46
    Activations Density 2.223%

    No Known Activations