© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12743
    Prev
    Next
    INDEX
    Explanations

    first and second person pronouns, along with the word "will" and the preposition "to".

    oai_token-act-pair · gemini-2.0-flash

    instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    writeFieldEnd
    -1.22
    MigrationBuilder
    -1.14
    webElementXpaths
    -1.14
    contentLoaded
    -1.10
     transférez
    -1.09
    fjspx
    -1.08
    UnusedPrivate
    -1.07
     Efq
    -1.05
    تقاوى
    -1.04
     itſelf
    -1.03
    POSITIVE LOGITS
    marginVertical
    0.40
    dateOfBirth
    0.37
     bolsos
    0.37
    wände
    0.35
    ruma
    0.35
     personalidade
    0.35
     stran
    0.34
     natureza
    0.33
     tisíc
    0.33
    わけではない
    0.32
    Activations Density 5.062%

    No Known Activations