© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9125
    Prev
    Next
    INDEX
    Explanations

    verbs and adjectives, sometimes with correlation with things like "important"

    oai_token-act-pair · gemini-2.0-flash

    past actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     recuerda
    -0.47
     slags
    -0.46
     íntima
    -0.45
    Více
    -0.44
     fitter
    -0.44
     def
    -0.43
    strokeWidth
    -0.42
     usata
    -0.42
     finger
    -0.42
    HIT
    -0.42
    POSITIVE LOGITS
     Audiodateien
    0.83
     betweenstory
    0.74
    帖最后由
    0.70
    AnchorStyles
    0.67
     protoimpl
    0.65
    WindowConstants
    0.65
     CreateTagHelper
    0.65
    uxxxx
    0.64
     AssemblyProduct
    0.63
    JvmStatic
    0.63
    Activations Density 3.061%

    No Known Activations