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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5672
    Prev
    Next
    INDEX
    Explanations

    words associated with lying, betrayal, and negative social interactions

    oai_token-act-pair · gemini-2.0-flash

    terms related to psychological traits and manipulation

    np_token-act-pair-logits · gpt-4o-mini

    Negative statements/deception

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    ंदीखरीदारी
    -0.69
    stridium
    -0.60
     Rahim
    -0.59
    Demografie
    -0.57
    исленность
    -0.55
    radic
    -0.55
    jerg
    -0.53
     Roscoe
    -0.52
    PreferredItem
    -0.51
     nawr
    -0.51
    POSITIVE LOGITS
     AssemblyTitle
    0.56
     henvisninger
    0.53
    endregion
    0.52
    nasi
    0.50
    UnusedPrivate
    0.49
    InSection
    0.47
    ISupport
    0.47
    ồng
    0.47
     BoxDecoration
    0.47
     AssemblyCompany
    0.46
    Activations Density 8.582%

    No Known Activations