© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2240
    Prev
    Next
    INDEX
    Explanations

    mentions of 'high school' or 'junior'

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word "high"

    np_token-act-pair-logits · gpt-4o-mini

    high

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ')['
    -0.55
    ⓘ
    -0.55
     sobą
    -0.45
    Kjelder
    -0.44
    '/',
    -0.42
    hau
    -0.42
    Referencies
    -0.42
    FFER
    -0.41
    ()">
    -0.41
    iel
    -0.41
    POSITIVE LOGITS
     الاطلاع
    0.69
    ScopeManager
    0.66
    ulemon
    0.65
    出版年
    0.63
    DataAnnotations
    0.63
     PropertyChanged
    0.62
    TagMode
    0.60
    BeginContext
    0.60
    WebElementEntity
    0.59
     Allociné
    0.57
    Activations Density 0.200%

    No Known Activations