INDEX

Explanations

forms of the verb "to be"

oai_token-act-pair · gemini-2.0-flash

be

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

-0.64

ly

-0.60

了

-0.59

-0.47

nya

-0.44

น

-0.43

-0.39

and

-0.38

ness

-0.37

less

-0.36

POSITIVE LOGITS

 poffe

0.93

 purpoſe

0.92

 ſtate

0.88

 uſed

0.88

Efq

0.85

 myſelf

0.83

 ſmall

0.83

 Jefus

0.82

 raiſ

0.82

 preſent

0.82

Activations Density 12.538%

forms of the verb "to be"

be

No Comments

No Known Activations