INDEX

Explanations

code, particularly function calls and variable assignments.

oai_token-act-pair · gemini-2.0-flash

code

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

 الحره

-0.71

 Wiktionnaire

-0.52

 '\\;'

-0.52

 reple

-0.51

 gratuitement

-0.50

AttributeSet

-0.49

InjectAttribute

-0.48

 للمعارف

-0.47

 acaso

-0.47

ValueStyle

-0.47

POSITIVE LOGITS

ofluor

0.64

TagMode

0.56

ViewImports

0.52

posables

0.51

setupUi

0.51

contentLoaded

0.51

nione

0.51

IsPostBack

0.51

 createSlice

0.51

forName

0.51

Activations Density 0.194%

code, particularly function calls and variable assignments.

code

No Comments

No Known Activations