© 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. 3504
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and terms used to describe special qualities

    oai_token-act-pair · gemini-2.0-flash

    unique

    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
     Majefty
    -0.75
     Wiktionnaire
    -0.70
     Houſe
    -0.65
     Anſ
    -0.64
     auffi
    -0.61
     houſe
    -0.60
    GEBURTS
    -0.60
    avorite
    -0.59
     PicClick
    -0.59
     fevere
    -0.59
    POSITIVE LOGITS
    itemBuilder
    0.46
    AutoField
    0.43
     and
    0.43
    velocityX
    0.42
     us
    0.42
     AttributeSet
    0.42
    dsi
    0.41
    keyCode
    0.41
    enumii
    0.41
     chuyện
    0.41
    Activations Density 6.786%

    No Known Activations