© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8404
    Prev
    Next
    INDEX
    Explanations

    words related to formal reporting around various fields of study and news events

    oai_token-act-pair · gemini-2.0-flash

    Publications and releases

    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
    Any
    -0.98
    any
    -0.94
     Any
    -0.88
     any
    -0.85
     cualquier
    -0.68
    ANY
    -0.66
    任何
    -0.65
     Cualquier
    -0.65
     أي
    -0.60
     ANY
    -0.58
    POSITIVE LOGITS
     a
    0.97
    inguém
    0.79
     lenker
    0.75
    ^(@)
    0.73
     an
    0.72
    ביוגרפיה
    0.71
     tfsi
    0.70
    MemoryWarning
    0.66
    LabelTagHelper
    0.65
    WriteBarrier
    0.63
    Activations Density 27.678%

    No Known Activations