INDEX

Explanations

code snippets with examples of return values and/or code execution.

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_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 surla

-0.59

קישורים

-0.57

polizei

-0.56

BrowserModule

-0.55

 pair

-0.52

Дереккөздер

-0.51

सन्दर्भ

-0.50

MotionEvent

-0.50

 للمعارف

-0.50

SequentialGroup

-0.50

POSITIVE LOGITS

 مشين

0.57

 ProtoMessage

0.56

NameInMap

0.52

 useDispatch

0.51

PreferredItem

0.49

sidemargin

0.49

+#+#

0.48

mkdirs

0.47

$_['

0.46

 Returned

0.45

Activations Density 2.358%

code snippets with examples of return values and/or code execution.

=>

No Comments

No Known Activations