© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10798
    Prev
    Next
    INDEX
    Explanations

    gibberish with some letters and numbers and some italian words

    oai_token-act-pair · gemini-2.0-flash

    names of things

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ]")]
    -0.92
     متعلقه
    -0.82
     ExecuteAsync
    -0.80
    +#+#
    -0.77
    AntiForgeryToken
    -0.77
    featureID
    -0.75
    oneofs
    -0.75
     disambiguazione
    -0.73
     AssemblyTitle
    -0.73
    SourceChecksum
    -0.72
    POSITIVE LOGITS
     cuci
    0.47
    gen
    0.45
    get
    0.43
    ials
    0.39
     personales
    0.37
    føre
    0.37
    漿
    0.36
     ce
    0.35
     get
    0.35
    chaffen
    0.34
    Activations Density 0.219%

    No Known Activations