© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12850
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and concepts relating to comparison, whether it be about the past vs present, or between two different things

    oai_token-act-pair · gemini-2.0-flash

    technical/scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ựng
    -0.69
     चीज़ों
    -0.65
     HasFactory
    -0.63
    oredCriteria
    -0.63
    spesies
    -0.60
    NameInMap
    -0.60
    enderror
    -0.57
    ="@+
    -0.57
     ftate
    -0.57
    verwijspagina
    -0.57
    POSITIVE LOGITS
    AnimationsModule
    0.55
     estekak
    0.42
    Sieg
    0.41
    multicolumn
    0.40
    ngths
    0.40
     setempat
    0.40
     both
    0.40
    นด์
    0.39
     nhất
    0.39
    swick
    0.39
    Activations Density 2.199%

    No Known Activations