© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3052
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "truth" or words related to truth

    oai_token-act-pair · gemini-2.0-flash

    truth

    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
    Negative Logits
    o
    -0.65
    <eos>
    -0.59
    issue
    -0.56
    Issue
    -0.52
    ↵↵
    -0.52
     ....
    -0.52
     issue
    -0.51
    ")]
    -0.51
     ..
    -0.49
     tendência
    -0.48
    POSITIVE LOGITS
     myſelf
    1.31
     Efq
    1.27
     poffe
    1.26
     itſelf
    1.20
     raiſ
    1.20
     pleaſure
    1.20
     Reſ
    1.17
     Eſ
    1.16
     juſt
    1.14
     purpoſe
    1.13
    Activations Density 1.682%

    No Known Activations