© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5556
    Prev
    Next
    INDEX
    Explanations

    mentions of "bad" or "good" in close proximity to the word "data" in C/C++ code

    oai_token-act-pair · gemini-2.0-flash

    C code buffer overflow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Roskov
    -1.30
     CreateTagHelper
    -1.19
     ModelExpression
    -1.13
     propOrder
    -1.09
     autorytatywna
    -1.09
    ftagPool
    -1.09
    GEBURTSDATUM
    -1.06
    AutoScaleMode
    -1.06
    AndEndTag
    -1.05
    principalTable
    -1.05
    POSITIVE LOGITS
    <bos>
    0.82
     in
    0.54
     for
    0.52
     to
    0.52
     and
    0.51
     no
    0.49
    .
    0.47
     at
    0.45
    ,
    0.44
     from
    0.43
    Activations Density 1.400%

    No Known Activations