INDEX

Explanations

US Marine Corps units and military-related terminology.

oai_token-act-pair · gemini-2.0-flash

manuals, documentation

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 '\\;'

-0.75

ArrowToggle

-0.73

URLException

-0.64

-0.57

#+#

-0.56

Parcelize

-0.56

 farine

-0.56

 polaire

-0.55

Rég

-0.54

 typelib

-0.54

POSITIVE LOGITS

帖最后由

0.49

章

0.45

 roboc

0.44

 Catalog

0.44

 catalog

0.44

ostatic

0.44

tomat

0.44

Rob

0.43

 ware

0.43

STS

0.43

Activations Density 0.611%

US Marine Corps units and military-related terminology.

manuals, documentation

No Known Activations