© 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. 8093
    Prev
    Next
    INDEX
    Explanations

    the prefix "pro"

    oai_token-act-pair · gemini-2.0-flash

    pro

    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
    IActionResult
    -0.58
    脚注の使い方
    -0.55
    TE
    -0.48
    Fio
    -0.48
    te
    -0.47
    hib
    -0.47
    tr
    -0.46
    Mend
    -0.46
     ***!
    -0.46
    oneofs
    -0.44
    POSITIVE LOGITS
     resourceCulture
    0.65
    ($__
    0.59
     HasFactory
    0.58
     nakalista
    0.58
    AddTagHelper
    0.54
     &___
    0.52
    ContentAsync
    0.51
    giveness
    0.51
     transfieras
    0.50
     Prus
    0.49
    Activations Density 1.194%

    No Known Activations