© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12467
    Prev
    Next
    INDEX
    Explanations

    words prefixed by "non-" or separated by a hyphen

    oai_token-act-pair · gemini-2.0-flash

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ⓧ
    -0.89
    RegressionTest
    -0.63
    '))
    -0.61
     "");
    -0.59
    Портал
    -0.57
    "));
    -0.56
    <bos>
    -0.56
     Jérusalem
    -0.55
     ""),
    -0.53
    -};
    -0.52
    POSITIVE LOGITS
    AxisAlignment
    0.73
    AddHtmlAttribute
    0.69
     BoxFit
    0.68
    PerformLayout
    0.68
    .
    0.66
    SerializedName
    0.65
     OnInit
    0.64
     Firstly
    0.62
     EdgeInsets
    0.60
    Firstly
    0.59
    Activations Density 1.212%

    No Known Activations