© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7220
    Prev
    Next
    INDEX
    Explanations

    the beginning or end of dialogue

    oai_token-act-pair · gemini-2.0-flash

    fictional dialog

    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
     ran
    -0.50
     let
    -0.47
     hit
    -0.46
     be
    -0.46
     sm
    -0.45
     where
    -0.44
    مر
    -0.44
     run
    -0.44
     repeated
    -0.44
     tri
    -0.43
    POSITIVE LOGITS
    GEBURTSDATUM
    1.17
     ModelExpression
    1.16
     الحره
    1.02
    SourceChecksum
    0.96
    AccessorTable
    0.91
    RenderAtEndOf
    0.88
     Jefus
    0.88
    tangentMode
    0.87
     Baillargeon
    0.85
    webElementXpaths
    0.83
    Activations Density 0.787%

    No Known Activations