© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6078
    Prev
    Next
    INDEX
    Explanations

    hyphenated phrases containing the word "initial" or "min"

    oai_token-act-pair · gemini-2.0-flash

    initial

    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
    enterOuterAlt
    -0.86
     CreateTagHelper
    -0.86
     <=",
    -0.85
    AndEndTag
    -0.84
    StructEnd
    -0.83
    TypedDataSet
    -0.79
     Himo
    -0.78
    IntoConstraints
    -0.77
     iprot
    -0.76
     محفوظة
    -0.76
    POSITIVE LOGITS
     P
    0.45
    的可
    0.43
    come
    0.43
    沙
    0.43
     joining
    0.43
     came
    0.43
    бро
    0.43
     come
    0.42
    带
    0.41
     action
    0.41
    Activations Density 0.089%

    No Known Activations