© 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. 11904
    Prev
    Next
    INDEX
    Explanations

    words that quantify in some way.

    oai_token-act-pair · gemini-2.0-flash

    different ways/explanations

    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
     r
    -1.16
     way
    -1.01
     Way
    -0.98
     ways
    -0.97
    Way
    -0.96
     Ways
    -0.89
     WAYS
    -0.88
    way
    -0.87
     WAY
    -0.82
    Ways
    -0.79
    POSITIVE LOGITS
    تقاوى
    0.56
     Савезне
    0.52
     autorytatywna
    0.52
    gebob
    0.52
    seteq
    0.52
    lename
    0.50
     Récup
    0.49
     fecond
    0.49
    ystick
    0.48
    MessageOf
    0.48
    Activations Density 7.353%

    No Known Activations