INDEX

Explanations

scientific language, particularly related to data and results with technical terms.

oai_token-act-pair · gemini-2.0-flash

words containing scientific terminology

np_token-act-pair-logits · gemini-2.0-flash

scientific spectra/analysis

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 AssemblyCompany

-0.82

HomeAsUpEnabled

-0.79

 StatefulWidget

-0.78

XmlEnum

-0.72

ngdoc

-0.70

expandindo

-0.68

interopRequire

-0.68

 StatelessWidget

-0.67

 onAnimation

-0.66

 AssemblyCulture

-0.65

POSITIVE LOGITS

дир

0.47

faz

0.45

θούν

0.44

lägg

0.43

fres

0.43

Brains

0.42

føre

0.42

avat

0.42

кисло

0.42

ORE

0.41

Activations Density 10.270%

scientific language, particularly related to data and results with technical terms.

words containing scientific terminology

scientific spectra/analysis

No Comments

No Known Activations