© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6055
    Prev
    Next
    INDEX
    Explanations

    code snippets and formatting

    oai_token-act-pair · gemini-2.0-flash

    underscore character

    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
     téléphonique
    -0.79
    FieldBuilder
    -0.71
    ValueStyle
    -0.69
    RenderAtEndOf
    -0.69
    AutoScaleMode
    -0.67
     للتو
    -0.63
    клопе
    -0.63
    scriptcase
    -0.61
    SequentialGroup
    -0.59
    CDCl
    -0.59
    POSITIVE LOGITS
    <bos>
    0.73
    DispatchToProps
    0.63
    minecraftforge
    0.50
     IBOutlet
    0.48
    RegressionTest
    0.46
    ssin
    0.45
    ://
    0.44
    ayanan
    0.43
     EdgeInsets
    0.42
    ņa
    0.42
    Activations Density 0.865%

    No Known Activations