© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12668
    Prev
    Next
    INDEX
    Explanations

    language related to students' academic status, often involving grades, school levels, and the process of being admitted or promoted.

    oai_token-act-pair · gemini-2.0-flash

    Students and education

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    úgó
    -0.80
     Completion
    -0.69
    RotationOrder
    -0.68
     дописавши
    -0.67
    Obrázky
    -0.66
     الرياضيه
    -0.63
    Completion
    -0.62
     ostavi
    -0.62
     @"/
    -0.60
    subject
    -0.59
    POSITIVE LOGITS
    findpost
    0.55
    ple
    0.45
     }}">
    0.44
    ars
    0.44
    Carriera
    0.43
    usermodel
    0.42
     en
    0.42
    
    0.42
    orsese
    0.41
    arsh
    0.40
    Activations Density 2.960%

    No Known Activations