INDEX

Explanations

contractions with the word "not"

oai_token-act-pair · gemini-2.0-flash

Contractions with "n't"

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

 "..\..\..\

-0.73

 propOrder

-0.70

transQ

-0.69

:✨

-0.69

writeField

-0.67

 Infórmanos

-0.65

IsContent

-0.62

قایناق‌لار

-0.61

يكب

-0.61

bootstrapcdn

-0.61

POSITIVE LOGITS

nt

0.99

’

0.94

0.93

not

0.74

not

0.69

0.64

NT

0.63

´

0.59

nt

0.58

Activations Density 1.037%

contractions with the word "not"

Contractions with "n't"

No Comments

No Known Activations