INDEX

Explanations

text related to gaming or Marvel entertainment franchises

oai_token-act-pair · gemini-2.0-flash

gaming, coding, fandom

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

InjectAttribute

-0.60

-0.57

 kasarigan

-0.57

#+#

-0.54

iesis

-0.50

-0.47

 format

-0.46

ufo

-0.45

toppers

-0.44

washingtonpost

-0.43

POSITIVE LOGITS

 itſelf

0.69

〢

0.69

 Houſe

0.66

 houſe

0.66

isContained

0.66

 Diſ

0.65

 Jefus

0.64

IVEREF

0.63

LEncoder

0.63

 becauſe

0.63

Activations Density 46.363%

text related to gaming or Marvel entertainment franchises

gaming, coding, fandom

No Comments

No Known Activations