© 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. 9721
    Prev
    Next
    INDEX
    Explanations

    mentions of truthfulness or verification, plus mentions of "people".

    oai_token-act-pair · gemini-2.0-flash

    indeed

    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
     Monfieur
    -1.46
     Efq
    -1.40
     Diſ
    -1.38
     ſtate
    -1.35
     itſelf
    -1.34
     resourceCulture
    -1.34
     ſta
    -1.31
     raiſ
    -1.28
     Reſ
    -1.28
     himſelf
    -1.27
    POSITIVE LOGITS
     
    0.91
    ing
    0.75
    s
    0.74
     I
    0.66
     r
    0.65
     to
    0.64
     causa
    0.60
     R
    0.60
     C
    0.59
     New
    0.59
    Activations Density 1.638%

    No Known Activations