INDEX

Explanations

words related to food and dining

oai_token-act-pair · gemini-2.0-flash

meat

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AutoresizingMask

-0.63

StructEnd

-0.55

ifflin

-0.51

 ویکی‌آمباردا

-0.49

CppCodeGen

-0.48

asun

-0.47

 мѣ

-0.46

 vilja

-0.46

 актив

-0.46

rungsseite

-0.45

POSITIVE LOGITS

 SwitchCompat

0.65

InjectAttribute

0.65

 &___

0.60

 незавершена

0.59

 conf

0.58

ⓧ

0.57

UnusedPrivate

0.53

lego

0.53

 Monza

0.53

 tire

0.51

Activations Density 1.799%

words related to food and dining

meat

No Comments

No Known Activations