© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15410
    Prev
    Next
    INDEX
    Explanations

    clauses set off by dashes or parenthesis

    oai_token-act-pair · gemini-2.0-flash

    dashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     resourceCulture
    -0.60
    —
    -0.55
    êche
    -0.55
     calendriers
    -0.54
    äch
    -0.53
    AddTagHelper
    -0.53
    ”—
    -0.52
    +[
    -0.51
     invokingState
    -0.51
    ─
    -0.50
    POSITIVE LOGITS
    WriteBarrier
    0.60
    FieldBuilder
    0.58
     становника
    0.58
    
    0.57
    ępo
    0.53
    yntaxException
    0.52
    <bos>
    0.52
     suena
    0.51
    zyła
    0.51
     bő
    0.50
    Activations Density 2.462%

    No Known Activations