© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2092
    Prev
    Next
    INDEX
    Explanations

    action words and conversational phrases involving persuasion

    oai_token-act-pair · gemini-2.0-flash

    communication/expression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    DotNetBar
    -0.65
    PhysRevLett
    -0.60
     &___
    -0.59
    strftime
    -0.59
    ContentAsync
    -0.58
    ConstraintMaker
    -0.56
    principalColumn
    -0.55
     Pyram
    -0.55
    newswire
    -0.54
    StoredProcedure
    -0.53
    POSITIVE LOGITS
     encontr
    0.49
     Hügel
    0.48
     Betracht
    0.47
    ész
    0.47
     szuka
    0.46
     chng
    0.46
     découv
    0.46
     preghiera
    0.45
     Weisheit
    0.45
     venganza
    0.45
    Activations Density 13.747%

    No Known Activations