© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6877
    Prev
    Next
    INDEX
    Explanations

    instances of the word "so,"

    oai_token-act-pair · gemini-2.0-flash

    so many/much

    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
    TagMode
    -0.83
    تقاوى
    -0.79
    FormTagHelper
    -0.66
    RenderAtEndOf
    -0.66
    +#+
    -0.63
    AccessorTable
    -0.63
    ConstraintMaker
    -0.62
     ArrayAdapter
    -0.60
    MANY
    -0.59
     المعيارى
    -0.59
    POSITIVE LOGITS
     may
    0.65
     Varma
    0.51
     lot
    0.51
    chers
    0.50
    ves
    0.48
    osuke
    0.48
    CompilerServices
    0.47
    atiles
    0.47
    iences
    0.47
    cale
    0.47
    Activations Density 3.889%

    No Known Activations