© 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. 6516
    Prev
    Next
    INDEX
    Explanations

    words connecting two ideas in a sentence like "to" and "and"

    oai_token-act-pair · gemini-2.0-flash

    fixing and improving

    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
    tagHelperRunner
    -0.61
     typelib
    -0.60
    ORMAL
    -0.56
    !*\
    -0.49
    hadur
    -0.48
    libft
    -0.48
     <<<<<<<<<<<<<<
    -0.48
    signable
    -0.47
    ecco
    -0.47
     Chwiliwch
    -0.47
    POSITIVE LOGITS
     up
    0.69
    ResponseWriter
    0.59
     Parish
    0.57
     Upan
    0.56
    up
    0.53
    
    0.51
     Sicilian
    0.49
     parish
    0.48
     Phoen
    0.48
    Parish
    0.48
    Activations Density 5.790%

    No Known Activations