© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14708
    Prev
    Next
    INDEX
    Explanations

    words related to business and marketing concepts, especially around successful products and satisfied customers.

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    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
     ModelExpression
    -0.84
     فريبيس
    -0.83
    GOTREF
    -0.80
     للمعارف
    -0.80
    AndEndTag
    -0.77
    matchCondition
    -0.77
     kasarigan
    -0.77
    PYX
    -0.75
    IntoConstraints
    -0.74
     leaves
    -0.74
    POSITIVE LOGITS
     annen
    0.40
     hjælp
    0.37
    령
    0.36
    zuf
    0.35
     universitaire
    0.35
     "..\..\
    0.34
     limpio
    0.34
    gæ
    0.33
     sakin
    0.33
    meni
    0.33
    Activations Density 14.609%

    No Known Activations