© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7490
    Prev
    Next
    INDEX
    Explanations

    positive descriptive language and conditional statements involving "if"

    oai_token-act-pair · gemini-2.0-flash

    quality

    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
    principalColumn
    -0.62
     Вікіпе
    -0.59
    unhofer
    -0.57
    perative
    -0.56
    gaged
    -0.54
    liano
    -0.53
    iterranée
    -0.53
     الاطلاع
    -0.52
    cinogen
    -0.51
    MMV
    -0.51
    POSITIVE LOGITS
     properly
    1.34
     well
    1.33
     Properly
    1.27
     correctly
    1.25
    properly
    1.20
     excellently
    1.20
     expertly
    1.19
     poorly
    1.15
     skillfully
    1.15
     nicely
    1.12
    Activations Density 0.984%

    No Known Activations