Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9622
    Prev
    Next
    INDEX
    Explanations

    mentions of politics and visual data representations

    oai_token-act-pair · gemini-2.0-flash

    colors

    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
     blue
    -2.09
     Blue
    -2.03
    Blue
    -1.95
     BLUE
    -1.95
    blue
    -1.95
     black
    -1.93
     yellow
    -1.92
     grey
    -1.90
     white
    -1.88
     gray
    -1.86
    POSITIVE LOGITS
     kasarigan
    0.76
    Geplaatst
    0.55
     onOptions
    0.48
    RefNanny
    0.47
    исленность
    0.45
     AssemblyCulture
    0.45
    HasAnnotation
    0.45
    ocardio
    0.44
    LookAnd
    0.44
    turnstile
    0.44
    Activations Density 1.754%

    No Known Activations