© 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. 10512
    Prev
    Next
    INDEX
    Explanations

    mentions of place names and situations

    oai_token-act-pair · gemini-2.0-flash

    Africa

    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
     okru
    -0.50
     model
    -0.48
     modelos
    -0.47
     serangga
    -0.47
     Henry
    -0.46
    JoinTable
    -0.45
    Ufficio
    -0.45
     Доро
    -0.45
    GeneratedValue
    -0.44
     Hanna
    -0.44
    POSITIVE LOGITS
    postIndex
    0.73
    GIVEREF
    0.67
     ब्रेकडाउन
    0.64
    CppCodeGen
    0.63
    twimg
    0.63
    INCREF
    0.60
     مُعرِّف
    0.60
    (',');
    0.56
     الحره
    0.56
    sonaro
    0.56
    Activations Density 0.666%

    No Known Activations