© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14054
    Prev
    Next
    INDEX
    Explanations

    text discussing strong conflicting emotions

    oai_token-act-pair · gemini-2.0-flash

    loves and hates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     HasFactory
    -0.90
     समीक्षक
    -0.77
    antMatchers
    -0.76
    
    -0.74
     समीक्षाओं
    -0.74
     lenker
    -0.73
     CreateTagHelper
    -0.73
     Efq
    -0.71
    eseorang
    -0.71
     IBOutlet
    -0.71
    POSITIVE LOGITS
    TagHelper
    0.44
    jsxFileName
    0.40
    ague
    0.40
     cận
    0.40
     yet
    0.39
    φαλ
    0.37
    iget
    0.37
    便
    0.35
    슬
    0.34
    別に
    0.34
    Activations Density 0.233%

    No Known Activations