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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11945
    Prev
    Next
    INDEX
    Explanations

    words associated with geometric layout and spatial arrangement

    oai_token-act-pair · gemini-2.0-flash

    vertical and horizontal formatting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     vertical
    -2.50
     Vertical
    -2.44
     horizontal
    -2.42
     Horizontal
    -2.39
    Vertical
    -2.30
    vertical
    -2.28
     vertically
    -2.28
    Horizontal
    -2.22
    horizontal
    -2.20
     horizontally
    -2.20
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.60
     NgModule
    0.53
     SafeMath
    0.52
    DialogFragment
    0.52
    vors
    0.52
    ագրություններ
    0.51
    EnableWeb
    0.51
     становника
    0.50
     ctypes
    0.49
    MathML
    0.46
    Activations Density 2.803%

    No Known Activations