INDEX

Explanations

text associated with labels and conversation quotes

oai_token-act-pair · gemini-2.0-flash

labeled

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

ChildIndex

-0.66

UnsafeEnabled

-0.65

 fhort

-0.61

 NSCoder

-0.57

TAWA

-0.55

 GenerationType

-0.54

◄

-0.54

 CommonModule

-0.53

 ویکی‌پدی

-0.52

<",

-0.52

POSITIVE LOGITS

waits

0.59

iega

0.52

wah

0.50

wikimedia

0.49

wah

0.48

bjs

0.48

alda

0.46

vergne

0.46

setOnAction

0.45

 forState

0.44

Activations Density 1.566%

text associated with labels and conversation quotes

labeled

No Comments

No Known Activations