INDEX

Explanations

the word "t" and words that end in "t" or are related to negativity

oai_token-act-pair · gemini-2.0-flash

"any"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 estekak

-0.49

more

-0.48

が増

-0.44

More

-0.43

longer

-0.43

 pisang

-0.41

elif

-0.41

 Longer

-0.41

 More

-0.41

 zaidi

-0.41

POSITIVE LOGITS

any

2.75

Any

2.11

Any

2.06

any

2.06

 cualquier

1.71

ANY

1.68

任何

1.68

 qualquer

1.66

ANY

1.49

 любые

1.42

Activations Density 4.140%

the word "t" and words that end in "t" or are related to negativity

"any"

No Comments

No Known Activations