© 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. 13880
    Prev
    Next
    INDEX
    Explanations

    language expressing necessity or requirement

    oai_token-act-pair · gemini-2.0-flash

    need/needs

    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
    ंदीखरीदारी
    -0.60
    HideFlags
    -0.56
    RenderAtEndOf
    -0.55
    +#+
    -0.55
    はじめに
    -0.52
     gainera
    -0.52
    WebVitals
    -0.51
     nahilalakip
    -0.50
    Šaltiniai
    -0.50
    AndEndTag
    -0.50
    POSITIVE LOGITS
    ſelf
    0.75
    ſelves
    0.73
     doubtnut
    0.71
     ſeveral
    0.71
     leſs
    0.69
     Jefus
    0.69
     iſt
    0.69
     Monfieur
    0.66
     Majefty
    0.65
     myſelf
    0.63
    Activations Density 6.769%

    No Known Activations