© 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. 8561
    Prev
    Next
    INDEX
    Explanations

    scientific language related to experimental results in brain research.

    oai_token-act-pair · gemini-2.0-flash

    of

    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
    ագրություններ
    -0.70
    出版年
    -0.68
    oredCriteria
    -0.65
    +#+#
    -0.65
    $_['
    -0.64
     ModelExpression
    -0.63
    IntoConstraints
    -0.63
     referenties
    -0.60
    complexContent
    -0.60
     мәкал
    -0.59
    POSITIVE LOGITS
    psychological
    0.51
     sơ
    0.51
     [],
    
    0.50
    erol
    0.49
     ''
    
    0.49
    knię
    0.47
     psychological
    0.47
    ButtonClicked
    0.47
     Sek
    0.47
     radar
    0.46
    Activations Density 5.833%

    No Known Activations