© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5121
    Prev
    Next
    INDEX
    Explanations

    strings of punctuation and parenthesis, often quotations marks, and sometimes tags like Algorithm

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     across
    -0.81
    Across
    -0.68
     overall
    -0.67
     round
    -0.67
     Across
    -0.66
    across
    -0.66
    Ārējās
    -0.64
    round
    -0.63
    overall
    -0.63
    board
    -0.59
    POSITIVE LOGITS
     quæ
    0.59
     murale
    0.59
    hidupan
    0.52
     culturelles
    0.52
     corporativa
    0.49
     religieuses
    0.49
    şen
    0.48
     habet
    0.48
     campagna
    0.47
     sabar
    0.47
    Activations Density 0.821%

    No Known Activations