© 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. 10801
    Prev
    Next
    INDEX
    Explanations

    language related to dedicated Michael Jackson fans and fan clubs

    oai_token-act-pair · gemini-2.0-flash

    fan communities

    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
     fan
    -3.09
     fans
    -3.08
     Fans
    -2.89
    Fans
    -2.75
    fans
    -2.69
     Fan
    -2.67
    Fan
    -2.67
    fan
    -2.55
    FAN
    -2.25
     FAN
    -2.17
    POSITIVE LOGITS
    GEBURTSDATUM
    0.52
    saraba
    0.49
     Berries
    0.46
    ensioni
    0.46
    contentLoaded
    0.44
    abestanden
    0.44
    ecuzione
    0.43
    mappedBy
    0.42
    DebuggerNonUser
    0.42
    protoc
    0.42
    Activations Density 1.277%

    No Known Activations