© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14116
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and identifiers

    oai_token-act-pair · gemini-2.0-flash

    code and configurations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     F
    -0.69
     
    -0.67
     I
    -0.67
     Is
    -0.65
    –
    -0.64
     (
    -0.63
     Z
    -0.62
     -
    -0.61
    -\
    -0.61
     Y
    -0.60
    POSITIVE LOGITS
     endwhile
    0.92
     كومونز
    0.91
     Efq
    0.90
     Савезне
    0.88
     تانيه
    0.86
     Theſe
    0.83
    IntoConstraints
    0.82
     Shakspeare
    0.82
    ագրություններ
    0.80
     Offisielt
    0.79
    Activations Density 3.711%

    No Known Activations