© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2993
    Prev
    Next
    INDEX
    Explanations

    segments of code with conditional if/else statements, likely within public/private functions involving "this.".

    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_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    MemoryWarning
    -0.63
    XmlAccessType
    -0.52
    TintMode
    -0.48
     inter
    -0.47
    mittags
    -0.46
     []:
    -0.44
    YMMV
    -0.44
     findOne
    -0.42
     sub
    -0.41
    żar
    -0.41
    POSITIVE LOGITS
    <bos>
    0.63
    aarrggbb
    0.56
    AxisAlignment
    0.54
    Geplaatst
    0.54
    ifikationer
    0.54
    MENAFN
    0.53
    GEL
    0.52
     laurel
    0.52
    خود
    0.52
    magitan
    0.52
    Activations Density 3.837%

    No Known Activations