INDEX

Explanations

technical scientific/legal/financial writing used in reports that often contain measurements

oai_token-act-pair · gemini-2.0-flash

actions or processes

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

<bos>

-0.55

rungsseite

-0.54

 TextAppearance

-0.52

 AppDelegate

-0.48

脚注の使い方

-0.48

vician

-0.47

ondheim

-0.46

 SwitchCompat

-0.46

 echa

-0.46

kün

-0.46

POSITIVE LOGITS

ValueStyle

0.70

MLLoader

0.64

QMetaType

0.63

AndroidJUnit

0.56

 الرياضيه

0.55

ГЛА

0.55

 transfieras

0.54

WireFormat

0.53

addCriterion

0.53

новниш

0.53

Activations Density 5.446%

technical scientific/legal/financial writing used in reports that often contain measurements

actions or processes

No Known Activations