© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6828
    Prev
    Next
    INDEX
    Explanations

    words related to written communication, instruction and difficulty

    oai_token-act-pair · gemini-2.0-flash

    letter, case, problem

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     ge
    -0.51
    orti
    -0.49
    gic
    -0.49
    obium
    -0.49
     ange
    -0.47
    lstm
    -0.45
    gil
    -0.45
     bal
    -0.45
    yscy
    -0.45
    "}")
    -0.44
    POSITIVE LOGITS
     AssemblyCulture
    0.88
    principalColumn
    0.77
    xnn
    0.69
    httphttps
    0.68
     ligiloj
    0.66
    :✨
    0.66
    SourceChecksum
    0.65
     onOptions
    0.63
    LookAnd
    0.60
     katanya
    0.57
    Activations Density 2.166%

    No Known Activations