© 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. 4245
    Prev
    Next
    INDEX
    Explanations

    the word "verified" (and perhaps its variants)

    oai_token-act-pair · gemini-2.0-flash

    verified

    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
     purpoſe
    -1.13
     pleaſure
    -1.13
     houſe
    -1.11
     Diſ
    -1.11
     ſtre
    -1.10
     ſta
    -1.09
     juſ
    -1.09
     leaſt
    -1.07
     ſtate
    -1.05
     Reſ
    -1.05
    POSITIVE LOGITS
    '
    0.85
     
    0.72
    (
    0.69
     A
    0.69
    A
    0.64
    ↵↵
    0.63
    C
    0.61
    ↵
    0.60
     C
    0.57
    _
    0.56
    Activations Density 1.648%

    No Known Activations