© 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. 8584
    Prev
    Next
    INDEX
    Explanations

    words or phrases associated with education, learning, or research, particularly when coupled with community, technology, or health

    oai_token-act-pair · gemini-2.0-flash

    Societal or political issues

    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
    Personendaten
    -0.64
    NameInMap
    -0.64
    </caption>
    -0.59
    DockStyle
    -0.59
    UnitTesting
    -0.58
     [*]
    -0.57
    Autoritní
    -0.57
     GenerationType
    -0.56
    dafx
    -0.56
    municipi
    -0.56
    POSITIVE LOGITS
    kloped
    0.65
     okuyayım
    0.50
    (".");
    0.50
    ільки
    0.48
     hoek
    0.48
     cửa
    0.47
    [:]
    0.45
    runners
    0.44
    }{$
    0.44
    יין
    0.44
    Activations Density 7.318%

    No Known Activations