© 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. 10977
    Prev
    Next
    INDEX
    Explanations

    mentions of "using" a methodology or tool, and related words such as "using", "use", "conducting", "perform", "implement" and words connecting to that tool or technique.

    oai_token-act-pair · gemini-2.0-flash

    use

    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
     use
    -1.10
    use
    -1.05
    Use
    -1.02
     Use
    -0.96
     uses
    -0.89
    USE
    -0.83
     uso
    -0.82
    uses
    -0.79
     Uses
    -0.78
     utilización
    -0.78
    POSITIVE LOGITS
     '\\;'
    1.01
    StructEnd
    0.88
    ArrowToggle
    0.87
     betweenstory
    0.85
    featureID
    0.85
     protoimpl
    0.85
     autorytatywna
    0.84
     utafitiHapana
    0.84
    ^(@)
    0.84
     snippetHide
    0.83
    Activations Density 9.162%

    No Known Activations