INDEX

Explanations

instructions or directions within technical documentation

oai_token-act-pair · gemini-2.0-flash

Computing and system administration

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 disambiguazione

-1.00

MigrationBuilder

-1.00

 Мексичка

-0.94

 myſelf

-0.94

Efq

-0.93

reportWebVitals

-0.93

AsUp

-0.92

 setInterval

-0.92

脚注の使い方

-0.90

PreferredItem

-0.90

POSITIVE LOGITS

“

0.43

0.42

オー

0.42

//

0.41

OR

0.41

RY

0.38

‘

0.38

 penge

0.37

<eos>

0.37

te

0.36

Activations Density 0.614%

instructions or directions within technical documentation

Computing and system administration

No Comments

No Known Activations