INDEX

Explanations

news article markers and section headers.

oai_token-act-pair · gemini-2.0-flash

)

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

<bos>

-0.62

 مرئيه

-0.54

bet

-0.43

ResponseWriter

-0.40

eni

-0.40

НИК

-0.39

BP

-0.39

reebok

-0.38

lí

-0.37

 IActionResult

-0.37

POSITIVE LOGITS

Efq

0.75

 myſelf

0.57

 ſmall

0.56

 ſeveral

0.56

 diſt

0.56

 purpoſe

0.53

 faſt

0.52

 Theſe

0.52

^(@)

0.52

 Shakspeare

0.52

Activations Density 0.218%

news article markers and section headers.

)

No Comments

No Known Activations