© 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. 11589
    Prev
    Next
    INDEX
    Explanations

    code and code comments

    oai_token-act-pair · gemini-2.0-flash

    #

    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
     purpoſe
    -0.77
    DrawerToggle
    -0.76
     ſtill
    -0.74
     Theſe
    -0.74
     Jefus
    -0.74
     Majefty
    -0.73
     كومونز
    -0.72
     Diſ
    -0.71
     houſe
    -0.71
    rungsseite
    -0.69
    POSITIVE LOGITS
    iastes
    0.46
     Vettel
    0.46
    PTION
    0.41
    URIComponent
    0.40
    +:+
    0.40
     Macron
    0.39
     Netanyahu
    0.39
     Pote
    0.38
    piro
    0.38
    Kontrola
    0.38
    Activations Density 1.867%

    No Known Activations