© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7153
    Prev
    Next
    INDEX
    Explanations

    code snippets with variable and method names

    oai_token-act-pair · gemini-2.0-flash

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     corse
    -0.42
    Datuak
    -0.41
    Zas
    -0.40
    牢
    -0.38
    like
    -0.38
     scratch
    -0.38
    no
    -0.38
    dra
    -0.38
    ok
    -0.36
     raw
    -0.36
    POSITIVE LOGITS
     يتيمه
    1.13
     nakalista
    1.01
    parsedMessage
    0.94
    AndEndTag
    0.88
    bootstrapcdn
    0.86
    tagHelperRunner
    0.83
     Exacts
    0.83
    énario
    0.76
     ProtoMessage
    0.76
    IntoConstraints
    0.76
    Activations Density 20.469%

    No Known Activations