© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9574
    Prev
    Next
    INDEX
    Explanations

    strings like "im" combined with apostrophes

    oai_token-act-pair · gemini-2.0-flash

    Technical/publication text

    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
     désolés
    -0.44
    ya
    -0.41
    ry
    -0.40
     il
    -0.40
    nak
    -0.39
    umen
    -0.39
     bes
    -0.39
    meleri
    -0.39
    ak
    -0.38
    reza
    -0.38
    POSITIVE LOGITS
     surla
    0.80
    AndEndTag
    0.77
    InSection
    0.73
    ^(@)
    0.71
    liferay
    0.70
    SharedDtor
    0.70
     NSCoder
    0.69
    DispatchToProps
    0.69
    MarshalTo
    0.67
    featureID
    0.66
    Activations Density 0.415%

    No Known Activations