© 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. 7738
    Prev
    Next
    INDEX
    Explanations

    words that describe something left behind or abandoned, as well as general negative descriptors

    oai_token-act-pair · gemini-2.0-flash

    remaining

    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
     CreateTagHelper
    -0.75
    EndGlobalSection
    -0.60
    Personendaten
    -0.57
     noDo
    -0.56
    رشف
    -0.55
     ویکی‌پدیا
    -0.55
    CodedInputStream
    -0.54
     Signalez
    -0.54
    Hentet
    -0.54
    Билгалдахарш
    -0.53
    POSITIVE LOGITS
     left
    1.55
     remaining
    1.44
     Remaining
    1.28
     Left
    1.27
     leftover
    1.24
     residual
    1.21
    留下
    1.21
    remaining
    1.20
    left
    1.19
     остав
    1.19
    Activations Density 1.066%

    No Known Activations