© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9381
    Prev
    Next
    INDEX
    Explanations

    references to actions or abilities involving weapons or fighting

    oai_token-act-pair · gemini-2.0-flash

    Kyuranger show

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    исленность
    -0.70
    InputBorder
    -0.66
    setVerticalGroup
    -0.65
     Roskov
    -0.59
    StoryboardSegue
    -0.57
    CodeAttribute
    -0.56
     linkovi
    -0.53
     ISNI
    -0.53
    soort
    -0.52
    AISSEE
    -0.51
    POSITIVE LOGITS
    MessageTagHelper
    0.57
     uintptr
    0.52
     trajets
    0.51
    Cyfeiriadau
    0.50
    OrEqual
    0.46
     gynhyrchwyd
    0.46
    <?>
    0.46
     protoimpl
    0.46
     na
    0.45
     Bone
    0.45
    Activations Density 2.990%

    No Known Activations