INDEX

Explanations

scientific lab related words (tubes, dish, etc.)

oai_token-act-pair · gemini-2.0-flash

scientific experiments involving tubes

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

 raiſ

-0.72

 Theſe

-0.67

 Reſ

-0.66

UnsafeEnabled

-0.60

EDEFAULT

-0.60

 itſelf

-0.60

:✨

-0.60

ArgsConstructor

-0.59

 theſe

-0.58

 Diſ

-0.57

POSITIVE LOGITS

mybatisplus

0.58

gården

0.58

 chắn

0.53

 μή

0.49

 Family

0.47

UNCH

0.47

ukunft

0.47

parian

0.47

LOGOUT

0.47

గా

0.46

Activations Density 1.033%

scientific lab related words (tubes, dish, etc.)

scientific experiments involving tubes

No Comments

No Known Activations