INDEX

Explanations

code snippets that include periods

oai_token-act-pair · gemini-2.0-flash

code snippets

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

🏾

-0.57

KKKK

-0.57

🏿

-0.57

例句

-0.56

NUMX

-0.56

Xuất

-0.55

RTEX

-0.55

 reaſon

-0.55

izarse

-0.54

createTextNode

-0.54

POSITIVE LOGITS

 okuyayım

0.50

 typelib

0.50

 gård

0.47

 فريبيس

0.46

 <=",

0.46

野

0.45

requipa

0.45

 prêtres

0.44

ち

0.44

WebElementEntity

0.44

Activations Density 0.289%

code snippets that include periods

code snippets

No Comments

No Known Activations