© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4697
    Prev
    Next
    INDEX
    Explanations

    code snippets with a large number of lines

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    PreferredItem
    -0.79
    Бахар
    -0.71
    RenderAtEndOf
    -0.69
    endphp
    -0.62
     ويكيميديا
    -0.59
     EdgeInsets
    -0.59
    UpInside
    -0.56
     Normdatei
    -0.56
    HomeAsUpEnabled
    -0.56
     FetchType
    -0.55
    POSITIVE LOGITS
     Efq
    0.69
     Monfieur
    0.66
     Majefty
    0.61
     Houſe
    0.57
     igenom
    0.56
     Reſ
    0.56
    ronpa
    0.55
     Theſe
    0.54
     Annales
    0.53
     contextLoads
    0.53
    Activations Density 1.317%

    No Known Activations