© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10013
    Prev
    Next
    INDEX
    Explanations

    gibberish strings of letters, especially 'de', 'be', 'ab', 'da', 'ce', 'fd', and 'ca'

    oai_token-act-pair · gemini-2.0-flash

    efe

    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
    abestanden
    -0.89
     الحره
    -0.85
    /*
    -0.77
    contentLoaded
    -0.74
    providedIn
    -0.72
    parsedMessage
    -0.72
     magnétique
    -0.70
     AssemblyCompany
    -0.69
    RenderAtEndOf
    -0.68
     coloré
    -0.68
    POSITIVE LOGITS
    <bos>
    0.58
     cour
    0.45
     he
    0.44
    ib
    0.44
    Cour
    0.44
    ticello
    0.43
    cius
    0.43
    digitalWrite
    0.41
    ibar
    0.41
    bre
    0.40
    Activations Density 0.372%

    No Known Activations