© 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. 8288
    Prev
    Next
    INDEX
    Explanations

    many common connecting words, but mostly the word "and" used to connect multiple things.

    oai_token-act-pair · gemini-2.0-flash

    Complex sentence structure

    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
    <bos>
    -0.57
     a
    -0.49
    を
    -0.47
    に
    -0.46
     là
    -0.46
    ↵↵
    -0.46
    a
    -0.45
    のが
    -0.45
    فر
    -0.44
    が
    -0.44
    POSITIVE LOGITS
     CreateTagHelper
    1.09
    StoryboardSegue
    0.99
    MemoryWarning
    0.97
    RenderAtEndOf
    0.95
    +#+#
    0.93
     lenker
    0.88
     myſelf
    0.87
    GEBURTSDATUM
    0.85
    tagHelperRunner
    0.84
     שוליים
    0.83
    Activations Density 4.429%

    No Known Activations