INDEX

Explanations

words related to competition, accomplishment, or progress

oai_token-act-pair · gemini-2.0-flash

Sports and business results

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

brainly

-0.54

 localObject

-0.49

Eacute

-0.48

 hiệu

-0.47

maxcdn

-0.47

erobic

-0.45

 useRouter

-0.45

copa

-0.44

 ποι

-0.43

SPA

-0.43

POSITIVE LOGITS

 Wikimedijinoj

0.77

 pleaſure

0.73

 Италијани

0.67

MessageOf

0.67

TintMode

0.64

 "..\..\..\

0.63

 postIndex

0.59

 diſt

0.59

 ſur

0.59

 every

0.57

Activations Density 4.319%

words related to competition, accomplishment, or progress

Sports and business results

No Comments

No Known Activations