© 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. 7805
    Prev
    Next
    INDEX
    Explanations

    language related to financial performance, planning, and position.

    oai_token-act-pair · gemini-2.0-flash

    strength

    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
     Flat
    -0.48
    flat
    -0.46
     (
    -0.43
     flat
    -0.43
     Metropolitana
    -0.42
    Flat
    -0.42
    lip
    -0.39
     SIM
    -0.39
    woordig
    -0.39
    lir
    -0.38
    POSITIVE LOGITS
     strength
    1.63
    strength
    1.52
     Strength
    1.45
    Strength
    1.43
     STRENGTH
    1.38
     strengthened
    1.36
     strengthen
    1.33
     strengthening
    1.32
     stronger
    1.30
    STRENGTH
    1.30
    Activations Density 0.646%

    No Known Activations