© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11415
    Prev
    Next
    INDEX
    Explanations

    general quantifying phrases using "to some" or "to the".

    oai_token-act-pair · gemini-2.0-flash

    degree or extent

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ViewFeatures
    -0.69
     OMITBAD
    -0.68
     onCancelled
    -0.66
    AutoresizingMask
    -0.66
     peindre
    -0.66
    heyd
    -0.65
    fisch
    -0.64
    PLICATIONS
    -0.64
     المعيارى
    -0.63
    médiaire
    -0.62
    POSITIVE LOGITS
    ch
    0.47
     withal
    0.44
    ANTLR
    0.41
     blisters
    0.40
    testens
    0.38
    eng
    0.36
    さて
    0.36
     initComponents
    0.35
     tait
    0.35
     corpor
    0.35
    Activations Density 4.590%

    No Known Activations