© 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. 4768
    Prev
    Next
    INDEX
    Explanations

    comparative phrases and numerical percentages

    oai_token-act-pair · gemini-2.0-flash

    usually

    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
    withstanding
    -0.63
     mergeFrom
    -0.60
     snippetHide
    -0.60
    湃
    -0.59
    matchCondition
    -0.58
    EndTag
    -0.58
     Accordingly
    -0.57
    lapsingToolbar
    -0.57
     accordingly
    -0.57
    AutoScaleMode
    -0.56
    POSITIVE LOGITS
     usually
    0.73
     typically
    0.71
     usual
    0.68
     HasFactory
    0.63
     normally
    0.62
     ordinarily
    0.61
     Usually
    0.60
     sonst
    0.60
     biasanya
    0.60
    typically
    0.60
    Activations Density 4.553%

    No Known Activations