© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1233
    Prev
    Next
    INDEX
    Explanations

    the word "know" and the first person pronoun "I"

    oai_token-act-pair · gemini-2.0-flash

    know

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     san
    -0.49
     (
    -0.47
    Morfologia
    -0.47
    dorp
    -0.47
     de
    -0.47
     Ten
    -0.47
     ten
    -0.47
     F
    -0.45
    __":
    -0.44
     den
    -0.44
    POSITIVE LOGITS
    +:+
    0.79
    AddTagHelper
    0.73
     doubtnut
    0.71
     Protestantism
    0.71
     løpet
    0.68
     pleaſure
    0.68
     itſelf
    0.65
    BeginContext
    0.65
     Hessian
    0.65
     geodes
    0.64
    Activations Density 0.089%

    No Known Activations