© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7935
    Prev
    Next
    INDEX
    Explanations

    words related to reading, writing, and media consumption, as well as general conversational interjections and qualifiers.

    oai_token-act-pair · gemini-2.0-flash

    actually

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     k
    -0.40
    _%
    -0.39
    ilius
    -0.39
     test
    -0.39
     tham
    -0.38
     kiin
    -0.37
     str
    -0.37
    licher
    -0.36
    dels
    -0.36
    -%
    -0.36
    POSITIVE LOGITS
     actually
    2.25
    actually
    2.16
     Actually
    1.94
    Actually
    1.89
     ACTUALLY
    1.80
     faktisk
    1.48
     eigenlijk
    1.48
    实际上
    1.46
     indeed
    1.45
    indeed
    1.42
    Activations Density 3.494%

    No Known Activations