INDEX

Explanations

mentions of maximum numeric amounts for things, as well as words like "users."

oai_token-act-pair · gemini-2.0-flash

Numerical amounts or Limits

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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>

-0.68

 utafitiHapana

-0.56

 للمعارف

-0.53

tså

-0.52

[]:

-0.52

štění

-0.50

 bağlantılar

-0.48

')):

-0.48

EXCEL

-0.47

inigungs

-0.46

POSITIVE LOGITS

AddHtmlAttribute

0.83

Становништво

0.65

labelledby

0.62

izr

0.61

openzeppelin

0.59

agerie

0.57

sizeCache

0.57

triangleq

0.56

 countable

0.56

 strepto

0.56

Activations Density 1.198%

mentions of maximum numeric amounts for things, as well as words like "users."

Numerical amounts or Limits

No Comments

No Known Activations