© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5611
    Prev
    Next
    INDEX
    Explanations

    long hexadecimal strings

    oai_token-act-pair · gemini-2.0-flash

    d

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     quæ
    -0.50
    ſelf
    -0.48
    bibinfo
    -0.40
     ſet
    -0.40
     Monfieur
    -0.39
     juſt
    -0.37
     whoſe
    -0.36
     deſt
    -0.36
     Efq
    -0.35
     uſed
    -0.35
    POSITIVE LOGITS
    WebVitals
    0.84
    XMLSchema
    0.77
    PyExc
    0.77
     ویکی‌پدی
    0.74
    TypedDataSet
    0.71
    EditorBrowsable
    0.69
    GOTREF
    0.69
    ftagPool
    0.68
    GIVEREF
    0.68
    aaa
    0.67
    Activations Density 2.592%

    No Known Activations