© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7459
    Prev
    Next
    INDEX
    Explanations

    words related to undermining or being detrimental, especially in the context of websites or legal matters

    oai_token-act-pair · gemini-2.0-flash

    credibility

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    Билгалдахарш
    -0.69
    ArrowToggle
    -0.66
    tagHelperRunner
    -0.66
    Portail
    -0.63
    جوايز
    -0.59
    enderror
    -0.58
    RenderAtEndOf
    -0.57
     estekak
    -0.57
     Treff
    -0.56
    Bronnen
    -0.55
    POSITIVE LOGITS
     credibility
    0.98
     authority
    0.92
     credible
    0.82
     credi
    0.80
    credi
    0.79
     CRED
    0.79
     professional
    0.77
     professionalism
    0.75
     kredi
    0.74
    authority
    0.74
    Activations Density 1.002%

    No Known Activations