© 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. 56
    Prev
    Next
    INDEX
    Explanations

    words related to scientific studies and analysis

    oai_token-act-pair · gemini-2.0-flash

    research papers

    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
    InitVars
    -0.55
    findpost
    -0.55
     ModelExpression
    -0.52
    kháu
    -0.52
     незавершена
    -0.52
     Obrador
    -0.52
    +#+#
    -0.52
    BASEPATH
    -0.52
    ThroughAttribute
    -0.49
     onOptions
    -0.48
    POSITIVE LOGITS
    Chham
    0.54
    cyd
    0.53
     jLabel
    0.51
     <<<<<<<<<<<<<<
    0.51
    Aholisi
    0.50
     GSA
    0.49
    riss
    0.49
    acea
    0.49
    transQ
    0.49
    MCE
    0.48
    Activations Density 18.337%

    No Known Activations