© 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. 12100
    Prev
    Next
    INDEX
    Explanations

    code or labels associated with data plots

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    RegressionTest
    -0.65
    رشف
    -0.63
    出版年
    -0.60
    expandindo
    -0.60
     beginnetje
    -0.60
     AssemblyTitle
    -0.60
    Portail
    -0.54
    PRNewswire
    -0.54
     Protección
    -0.54
    onActivityResult
    -0.54
    POSITIVE LOGITS
     gracilis
    0.65
     diameters
    0.56
     clustering
    0.56
     granite
    0.56
     hysteresis
    0.55
     calyx
    0.54
     Bracken
    0.54
     lichen
    0.54
    clustering
    0.53
     cylinders
    0.52
    Activations Density 11.556%

    No Known Activations