© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14111
    Prev
    Next
    INDEX
    Explanations

    C code snippets, particularly those involving `fprintf`, `goto`, and ioctl calls related to specific hardware or device operations

    oai_token-act-pair · gemini-2.0-flash

    goto

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     betweenstory
    -0.61
    Obrázky
    -0.61
    +#+#
    -0.54
    UNTAS
    -0.53
    VIAF
    -0.51
     Benfica
    -0.50
    ValueStyle
    -0.50
     sfondo
    -0.49
    gène
    -0.49
    diven
    -0.49
    POSITIVE LOGITS
     snippetHide
    0.68
    بوابة
    0.54
     anch
    0.54
     BoxDecoration
    0.52
    Портал
    0.51
    mergeFrom
    0.51
    Біографія
    0.49
     "..\..\
    0.49
     "..\..\..\
    0.49
    Personendaten
    0.49
    Activations Density 2.725%

    No Known Activations