© 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. 10903
    Prev
    Next
    INDEX
    Explanations

    bracketed expressions and the words "Touchable" and "item"

    oai_token-act-pair · gemini-2.0-flash

    Code/config files

    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
     Schar
    -0.60
     Sku
    -0.54
     Jeremy
    -0.54
     McGu
    -0.53
    Jeremy
    -0.51
     McColl
    -0.51
     Leno
    -0.51
     Wis
    -0.50
    dataGridView
    -0.50
    ubakar
    -0.50
    POSITIVE LOGITS
     Shakspeare
    0.71
     Efq
    0.69
    UnsafeEnabled
    0.66
    omio
    0.65
     pleaf
    0.65
    ]--;
    0.64
     Apocalypse
    0.63
     Inches
    0.63
     Triassic
    0.63
     purpoſe
    0.61
    Activations Density 8.372%

    No Known Activations