INDEX

Explanations

the word "excuse"

oai_token-act-pair · gemini-2.0-flash

excuse

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 CreateTagHelper

-1.23

 متعلقه

-1.02

AddTagHelper

-0.99

setVerticalGroup

-0.93

Lähteet

-0.93

 ويكيپ

-0.93

⏡

-0.93

drawSprites

-0.92

𓍊

-0.91

 PeEn

-0.91

POSITIVE LOGITS

<bos>

2.56

↵↵

1.30

1.05

↵

1.01

’

0.88

0.71

The

0.69

‘

0.68

0.66

0.64

Activations Density 1.012%

the word "excuse"

excuse

No Comments

No Known Activations

the word "excuse"

excuse

No Comments

No Known Activations