© 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. 4308
    Prev
    Next
    INDEX
    Explanations

    references to figures in a document

    oai_token-act-pair · gemini-2.0-flash

    Fig

    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
    djangoproject
    -0.96
     pinulongan
    -0.86
    makeConstraints
    -0.85
    rungsseite
    -0.84
    IntoConstraints
    -0.82
    +#+#
    -0.82
    Personendaten
    -0.81
    parsedMessage
    -0.81
    Sucesor
    -0.76
    providedIn
    -0.74
    POSITIVE LOGITS
     .
    0.60
    .
    0.51
    le
    0.48
    UI
    0.48
    ge
    0.45
    u
    0.44
    px
    0.44
    ue
    0.44
    uo
    0.43
    ak
    0.42
    Activations Density 2.660%

    No Known Activations