INDEX

Explanations

words related to food, especially Indian breads and desserts

oai_token-act-pair · gemini-2.0-flash

Pastries

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 CreateTagHelper

-0.64

issory

-0.54

 فريبيس

-0.54

InjectAttribute

-0.54

φάλ

-0.54

حياتها

-0.52

 fièvre

-0.52

LEAR

-0.49

حوالہ

-0.49

kijk

-0.49

POSITIVE LOGITS

Past

0.66

 Past

0.65

 flaky

0.61

past

0.60

 rolls

0.58

 croissants

0.57

 frit

0.56

 crepe

0.56

 chur

0.54

LEn

0.54

Activations Density 0.635%

words related to food, especially Indian breads and desserts

Pastries

No Comments

No Known Activations