© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11890
    Prev
    Next
    INDEX
    Explanations

    code blocks and variable assignments, with a preference for code related to thermal management and object property handling

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ;}
    -0.72
    "";
    -0.68
    /;
    -0.67
    
    -0.67
    ;");
    -0.67
     "";
    -0.64
    ();
    -0.63
    »;
    -0.60
     '/';
    -0.60
    //};
    -0.59
    POSITIVE LOGITS
     defaultstate
    0.70
     صوتيه
    0.65
    GenerationType
    0.63
    internalType
    0.57
    sizeCache
    0.57
    ngdoc
    0.56
    AccessFile
    0.54
    stateMutability
    0.54
     متعلقه
    0.53
    RegistryLite
    0.53
    Activations Density 8.049%

    No Known Activations