© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 16211
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to teaching and helping children

    oai_token-act-pair · gemini-2.0-flash

    teaching and education

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     teaching
    -0.73
     Teaching
    -0.66
    Teaching
    -0.65
    teaching
    -0.62
     '\\;'
    -0.58
    LookAnd
    -0.57
     teaches
    -0.56
    NameInMap
    -0.55
     TEACHING
    -0.54
    __(/*!
    -0.53
    POSITIVE LOGITS
     ModelExpression
    0.64
    byr
    0.57
    cerely
    0.56
    onViewCreated
    0.56
    meid
    0.56
    NameValuePair
    0.56
    出版年
    0.54
    httphttps
    0.52
    stücke
    0.52
    anyol
    0.52
    Activations Density 3.808%

    No Known Activations