INDEX

Explanations

words that are parts of recipes or restaurant reviews

oai_token-act-pair · gemini-2.0-flash

food and recipes

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 prostu

-0.51

 кӀ

-0.47

sem

-0.46

Sem

-0.46

nellement

-0.43

anz

-0.43

 señ

-0.42

 Rosenthal

-0.42

Sem

-0.42

POSITIVE LOGITS

AutoresizingMask

0.78

parsedMessage

0.77

oredCriteria

0.75

setVerticalGroup

0.71

Hochspringen

0.71

MessageOf

0.70

 FRESH

0.69

 contextLoads

0.68

Diweddarwch

0.66

AccessorTable

0.65

Activations Density 1.133%

words that are parts of recipes or restaurant reviews

food and recipes

No Comments

No Known Activations