INDEX

Explanations

the definite article "the"

oai_token-act-pair · gemini-2.0-flash

the

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

ondi

-0.55

 diamants

-0.53

 alrededores

-0.52

yours

-0.51

 vostri

-0.50

 alluminio

-0.48

 rayures

-0.48

 sogni

-0.48

 enged

-0.47

ugal

-0.47

POSITIVE LOGITS

leria

0.72

bootstrapcdn

0.69

็จ

0.60

riwal

0.60

tagHelperRunner

0.59

ंदीखरीदारी

0.58

 onCancelled

0.58

MLLoader

0.57

 initComponents

0.57

 Kombat

0.57

Activations Density 0.214%

the definite article "the"

the

No Comments

No Known Activations