INDEX

Explanations

the word 'the' and possessive words like "our", "your", or words ending in 's'

oai_token-act-pair · gemini-2.0-flash

Geographic regions

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

UnifiedTopology

-0.61

 kasarigan

-0.60

TestingModule

-0.56

parsedMessage

-0.56

NameInMap

-0.53

 Jefus

-0.52

DoubleQuotes

-0.50

principalTable

-0.49

ContentAsync

-0.47

 afield

-0.47

POSITIVE LOGITS

 state

0.66

 thiệu

0.60

 nation

0.60

 commonwealth

0.54

úrate

0.54

 State

0.52

 country

0.51

CAPTION

0.51

்கு

0.51

staat

0.50

Activations Density 1.012%

the word 'the' and possessive words like "our", "your", or words ending in 's'

Geographic regions

No Comments

No Known Activations