INDEX

Explanations

the word "the," sometimes emphasizing its significance to nearby words like those expressing time or importance.

oai_token-act-pair · gemini-2.0-flash

the

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Houſe

-0.97

 houſe

-0.90

 myſelf

-0.88

Efq

-0.85

 vœux

-0.84

 Monfieur

-0.84

 Majefty

-0.81

 Cæsar

-0.80

 jouets

-0.79

 ſeveral

-0.79

POSITIVE LOGITS

ri

0.57

0.56

ver

0.55

0.53

osh

0.53

“

0.53

 mergeFrom

0.52

cshtml

0.52

me

0.52

Activations Density 2.255%

the word "the," sometimes emphasizing its significance to nearby words like those expressing time or importance.

the

No Comments

No Known Activations