© 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. 3320
    Prev
    Next
    INDEX
    Explanations

    lists of steps or components

    oai_token-act-pair · gemini-2.0-flash

    Enumeration of steps/components

    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
    allure
    -0.55
    ArgumentParser
    -0.48
    SO
    -0.47
    AndEndTag
    -0.47
    INC
    -0.46
    mente
    -0.45
    heureusement
    -0.45
    so
    -0.44
    ocera
    -0.44
     tra
    -0.43
    POSITIVE LOGITS
    ReusableCell
    0.89
    mybatisplus
    0.86
     समीक्षाओं
    0.76
     <<<<<<<<<<<<<<
    0.68
    évaluateur
    0.68
    protoimpl
    0.67
    expandindo
    0.67
    AutoScaleMode
    0.67
     GlobalKey
    0.67
    LabelTagHelper
    0.64
    Activations Density 7.839%

    No Known Activations