INDEX

Explanations

words and phrases used to evaluate strength or importance

oai_token-act-pair · gemini-2.0-flash

most/more

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

 myſelf

-1.07

Efq

-1.01

 itſelf

-1.01

 purpoſe

-0.95

 poffible

-0.94

 uſed

-0.91

 raiſ

-0.91

новништво

-0.88

 ſeveral

-0.88

 fufficient

-0.87

POSITIVE LOGITS

da

0.58

Da

0.58

par

0.52

Da

0.46

con

0.46

pro

0.45

en

0.44

Ha

0.44

Con

0.43

vor

0.43

Activations Density 2.422%

words and phrases used to evaluate strength or importance

most/more

No Comments

No Known Activations