© 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. 6648
    Prev
    Next
    INDEX
    Explanations

    the shortened form of "literature" or the prefix "lit-"

    oai_token-act-pair · gemini-2.0-flash

    lit/literature

    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
     ga
    -0.52
    dafx
    -0.44
    icksburg
    -0.44
    脚注の使い方
    -0.44
     ExecuteAsync
    -0.43
     dây
    -0.43
    ga
    -0.43
     utafitiHapana
    -0.43
    waite
    -0.42
    hamel
    -0.42
    POSITIVE LOGITS
     purpoſe
    0.61
     Efq
    0.60
    ContentAsync
    0.57
     Toussaint
    0.57
    einander
    0.55
    олові
    0.55
    DataPropertyName
    0.54
     ſmall
    0.54
     Kram
    0.53
     itſelf
    0.53
    Activations Density 0.541%

    No Known Activations