© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4112
    Prev
    Next
    INDEX
    Explanations

    negations, comparisons, and contradictions

    oai_token-act-pair · gemini-2.0-flash

    justification or lack thereof

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    OGND
    -1.15
    tagHelperRunner
    -1.15
    HasIndex
    -1.05
     AssemblyCulture
    -1.00
    InjectAttribute
    -0.99
    EndContext
    -0.90
     tartalomajánló
    -0.90
    Sklici
    -0.89
     ProtoMessage
    -0.88
     ExecuteAsync
    -0.88
    POSITIVE LOGITS
     them
    0.49
     the
    0.48
     complete
    0.47
    koff
    0.46
    atz
    0.45
     a
    0.45
     various
    0.43
     one
    0.43
     Then
    0.43
     master
    0.43
    Activations Density 4.832%

    No Known Activations