INDEX

Explanations

words and phrases related to conflict and disease treatment

oai_token-act-pair · gemini-2.0-flash

fighting/defense/legal

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 against

-3.14

against

-2.91

 Against

-2.89

Against

-2.89

 AGAINST

-2.48

 contre

-2.03

 gegen

-1.95

 tegen

-1.71

 против

-1.63

 melawan

-1.48

POSITIVE LOGITS

 springfox

0.55

 Riau

0.51

 nahilalakip

0.50

GOTREF

0.48

abestanden

0.47

PointerException

0.47

 <>",

0.47

 Throwable

0.45

 BorderRadius

0.44

 bidet

0.44

Activations Density 3.461%

words and phrases related to conflict and disease treatment

fighting/defense/legal

No Comments

No Known Activations

words and phrases related to conflict and disease treatment

fighting/defense/legal

No Comments

No Known Activations