© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8339
    Prev
    Next
    INDEX
    Explanations

    words of subjective evaluation and the discussion of objective facts.

    oai_token-act-pair · gemini-2.0-flash

    Proper nouns

    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
     Normdatei
    -1.04
    ftagPool
    -1.01
     ComVisible
    -0.99
    WriteTagHelper
    -0.99
    WebVitals
    -0.94
     defaultstate
    -0.94
     AssemblyCulture
    -0.93
    protoimpl
    -0.91
     CreateTagHelper
    -0.90
    LookAnd
    -0.90
    POSITIVE LOGITS
     amyloid
    0.75
     Conspiracy
    0.73
     Virat
    0.72
     Reels
    0.71
     Evita
    0.71
     Silvio
    0.70
     Cerebral
    0.70
     Priscilla
    0.70
     Britney
    0.70
     Sauvignon
    0.69
    Activations Density 92.880%

    No Known Activations