© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15347
    Prev
    Next
    INDEX
    Explanations

    code snippets or variable names, particularly those starting with "RT", "RV", "F", or "com"

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    pulumi
    -0.49
    featureID
    -0.48
    getDoctrine
    -0.47
    chtenstein
    -0.47
    例句
    -0.47
     COMPLE
    -0.46
    FirstResponder
    -0.46
    basicConfig
    -0.45
    aarrggbb
    -0.45
    wikk
    -0.44
    POSITIVE LOGITS
    iastes
    0.57
    pensive
    0.56
    BeginInit
    0.56
     CreateTagHelper
    0.55
    нциклопе
    0.55
     vermelhas
    0.55
    gbaar
    0.54
     protoimpl
    0.54
    archiviato
    0.53
    rentiel
    0.52
    Activations Density 1.168%

    No Known Activations