© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1927
    Prev
    Next
    INDEX
    Explanations

    positive language or language related to opportunities

    oai_token-act-pair · gemini-2.0-flash

    a

    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
     ways
    -0.60
     avenues
    -0.53
     platforms
    -0.50
     Ways
    -0.49
    lementary
    -0.48
     sources
    -0.48
     source
    -0.47
     means
    -0.46
     Means
    -0.46
    ichen
    -0.46
    POSITIVE LOGITS
    addCriterion
    0.82
    
    0.72
     незавершена
    0.70
    ArrowToggle
    0.65
    isSuccessful
    0.64
     NSCoder
    0.63
    execSQL
    0.63
    AppMethodBeat
    0.61
    ModelAdmin
    0.59
    JspWriter
    0.59
    Activations Density 7.410%

    No Known Activations