© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2638
    Prev
    Next
    INDEX
    Explanations

    conversational filler words and punctuation

    oai_token-act-pair · gemini-2.0-flash

    well

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    DataAnnotations
    -0.54
     cref
    -0.54
    ssssssss
    -0.53
    !...
    -0.53
     thyself
    -0.52
    …!
    -0.52
     understatement
    -0.51
     Riti
    -0.51
    sssss
    -0.50
     Eben
    -0.50
    POSITIVE LOGITS
    <bos>
    0.73
    IContainer
    0.56
     ProtoMessage
    0.53
    Aktualisiert
    0.53
    Parameterized
    0.51
    yntaxException
    0.51
    XMLSchema
    0.50
    gelijk
    0.49
     Red
    0.48
     correctes
    0.48
    Activations Density 1.848%

    No Known Activations