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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10667
    Prev
    Next
    INDEX
    Explanations

    negative legal and media mentions of famous people, especially in cases involving murder or injustice.

    oai_token-act-pair · gemini-2.0-flash

    Michael Jackson

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    protoimpl
    -0.90
     NSCoder
    -0.74
    elemField
    -0.69
    Coordenadas
    -0.65
    Autoritní
    -0.63
    abestanden
    -0.62
    CrossRef
    -0.62
     فريبيس
    -0.60
    Fordítás
    -0.59
    Referanser
    -0.59
    POSITIVE LOGITS
     Abgerufen
    0.52
    ECI
    0.45
    pion
    0.44
     Marlene
    0.44
     star
    0.43
     pin
    0.42
     unbound
    0.42
    umpad
    0.41
    [++
    0.41
    marle
    0.41
    Activations Density 1.373%

    No Known Activations