© 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. 4309
    Prev
    Next
    INDEX
    Explanations

    names of places in Poland, particularly administrative districts and regions

    oai_token-act-pair · 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
    TagMode
    -0.83
    SourceChecksum
    -0.73
    esez
    -0.65
    Referanser
    -0.63
    Demografía
    -0.61
    SequentialGroup
    -0.58
    uxxxx
    -0.57
    MathML
    -0.57
     متعلقه
    -0.57
    Participating
    -0.55
    POSITIVE LOGITS
    AutoScaleMode
    0.57
    SpringBootTest
    0.46
    GEBURTSDATUM
    0.45
    oneofs
    0.45
    }>;
    0.42
    behandling
    0.42
    */),
    0.41
     up
    0.40
    kå
    0.40
    󠁣
    0.40
    Activations Density 0.049%

    No Known Activations