© 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. 13845
    Prev
    Next
    INDEX
    Explanations

    questions that begin with the word "how"

    oai_token-act-pair · gemini-2.0-flash

    How

    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
    VersionUID
    -0.96
    AccessorTable
    -0.96
    MigrationBuilder
    -0.90
    parsedMessage
    -0.82
    CppMethod
    -0.82
     ComVisible
    -0.81
    awtextra
    -0.81
    uxxxx
    -0.80
    writeFieldEnd
    -0.80
     nakalista
    -0.77
    POSITIVE LOGITS
     fine
    0.38
    l
    0.35
     Middle
    0.35
    ching
    0.34
    n
    0.33
    vere
    0.33
    em
    0.33
    times
    0.32
     long
    0.32
     tough
    0.31
    Activations Density 0.727%

    No Known Activations