© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6789
    Prev
    Next
    INDEX
    Explanations

    words relating to clothing, especially when worn

    oai_token-act-pair · gemini-2.0-flash

    wearing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    fromnode
    -0.62
    MemoryWarning
    -0.54
    zan
    -0.49
     الفلك
    -0.48
    anair
    -0.47
    ніципалі
    -0.47
     protoimpl
    -0.46
    mjs
    -0.45
    %\
    -0.45
    InstanceState
    -0.45
    POSITIVE LOGITS
    MigrationBuilder
    0.91
     saites
    0.70
    Sucesor
    0.64
    قایناق‌لار
    0.57
    findpost
    0.57
    migrationBuilder
    0.55
    MessageOf
    0.55
    Autoritní
    0.54
    estacks
    0.53
     defStyleAttr
    0.52
    Activations Density 4.228%

    No Known Activations