© 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. 12165
    Prev
    Next
    INDEX
    Explanations

    snippets of code or names that may be related to fictional characters

    oai_token-act-pair · gemini-2.0-flash

    Code and foreign languages

    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
    eningen
    -0.57
    IntoConstraints
    -0.53
     soigne
    -0.52
     Stras
    -0.50
    least
    -0.48
     least
    -0.48
    GenerationType
    -0.48
     Хотя
    -0.48
    véni
    -0.48
     endfor
    -0.48
    POSITIVE LOGITS
    WebVitals
    0.91
     autorytatywna
    0.66
     مشين
    0.65
     transfieras
    0.61
     للمعارف
    0.58
    UrlResolution
    0.57
    igshid
    0.56
    elemField
    0.55
    ">//
    0.55
    WithIOException
    0.54
    Activations Density 0.497%

    No Known Activations