© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10829
    Prev
    Next
    INDEX
    Explanations

    code and numbers, possibly extracting information about software configurations

    oai_token-act-pair · gemini-2.0-flash

    Tag

    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
    httphttps
    -0.98
    ContentAsync
    -0.86
    tvguidetime
    -0.85
    sizeCache
    -0.80
     MotionEvent
    -0.76
    StructEnd
    -0.75
    __':
    -0.74
    webElementGuid
    -0.72
     NSCoder
    -0.71
     nakalista
    -0.71
    POSITIVE LOGITS
    ಲ್ಲ
    0.47
    πο
    0.47
     able
    0.44
    huana
    0.43
    alle
    0.43
    aya
    0.42
    ý
    0.42
     p
    0.41
     memp
    0.41
    ल्
    0.41
    Activations Density 29.909%

    No Known Activations