© 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. 1081
    Prev
    Next
    INDEX
    Explanations

    words associated with business management, operations, and planning.

    oai_token-act-pair · gemini-2.0-flash

    systems

    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
    izr
    -0.54
     Band
    -0.44
    Viited
    -0.43
    ryu
    -0.41
     lone
    -0.41
     Bee
    -0.41
     Bro
    -0.40
    Ễ
    -0.40
     Forman
    -0.40
    qrstuvwxyz
    -0.40
    POSITIVE LOGITS
    رشف
    0.82
    tvguidetime
    0.71
    \{\\
    0.70
    GEBURTSDATUM
    0.66
     "..\..\..\
    0.66
     snippetHide
    0.65
     متعلقه
    0.65
     للمعارف
    0.62
    GraphicsUnit
    0.61
    تقاوى
    0.61
    Activations Density 10.436%

    No Known Activations