© 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. 2704
    Prev
    Next
    INDEX
    Explanations

    code snippets with numbers and symbols related to function definitions and conditional statements

    oai_token-act-pair · gemini-2.0-flash

    syntax related to programming functions or methods

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

    code/non-English

    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
     كومونز
    -0.79
    .*")]
    -0.73
    bitat
    -0.70
     الحره
    -0.69
    ](#
    -0.66
    aarrggbb
    -0.64
    RegistryLite
    -0.64
    QMetaType
    -0.63
    sidemargin
    -0.61
    ]")]
    -0.60
    POSITIVE LOGITS
     iVar
    0.50
     createSlice
    0.47
    kolwiek
    0.46
     pitä
    0.46
     řek
    0.45
     imagine
    0.45
    principalTable
    0.45
    solicitud
    0.45
    CppMethod
    0.44
     jöv
    0.43
    Activations Density 0.862%

    No Known Activations