© 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. 4922
    Prev
    Next
    INDEX
    Explanations

    what appear to be references, indices, codes, or model numbers

    oai_token-act-pair · gemini-2.0-flash

    car models

    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
     untrue
    -0.96
     FALSE
    -0.73
     false
    -0.73
    false
    -0.70
     False
    -0.67
    FALSE
    -0.66
     incorrect
    -0.66
    False
    -0.63
     true
    -0.60
     True
    -0.60
    POSITIVE LOGITS
    IntoConstraints
    0.77
    LookAnd
    0.71
    AndEndTag
    0.65
    HtmlAttribute
    0.62
     pleaſure
    0.53
     виправивши
    0.50
    Wart
    0.49
     überw
    0.48
     shogun
    0.47
    "],
    0.47
    Activations Density 0.323%

    No Known Activations