© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10241
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially C++ and Javascript, which includes terms like "assert", "mark", "instance", and "symbol".

    oai_token-act-pair · gemini-2.0-flash

    mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    })();
    -0.59
    /******/
    -0.59
    AndroidJUnit
    -0.58
    InjectMocks
    -0.55
    ++];
    -0.53
    SourceChecksum
    -0.53
    phazard
    -0.52
     getItem
    -0.52
    voort
    -0.52
     original
    -0.51
    POSITIVE LOGITS
     visualizing
    0.69
     asiatique
    0.68
     dirait
    0.68
    EClass
    0.67
    Espèce
    0.67
     brancas
    0.66
     Monticello
    0.66
     poches
    0.65
    tagHelperRunner
    0.65
     tasche
    0.65
    Activations Density 1.916%

    No Known Activations