© 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. 8603
    Prev
    Next
    INDEX
    Explanations

    instances of someone completing or attending an educational program.

    oai_token-act-pair · gemini-2.0-flash

    Education/school

    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
     law
    -0.94
     Law
    -0.82
    Law
    -0.81
    law
    -0.78
    LAW
    -0.72
    WithMany
    -0.68
     LAW
    -0.66
    Chemistry
    -0.62
     avoient
    -0.58
    zzleHttp
    -0.58
    POSITIVE LOGITS
    ibouti
    0.59
     viewDidLoad
    0.56
    batore
    0.55
     defaultstate
    0.53
     BIBLIO
    0.53
     Educational
    0.52
     Education
    0.50
    stateMutability
    0.49
    Education
    0.48
    SourceChecksum
    0.48
    Activations Density 2.892%

    No Known Activations