INDEX

Explanations

language about special education or disabilities

oai_token-act-pair · gemini-2.0-flash

with

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

crollView

-0.51

/*

-0.49

כך

-0.47

 intestine

-0.46

stdafx

-0.46

Története

-0.46

헌

-0.46

HasIndex

-0.45

 deaf

-0.45

 sick

-0.44

POSITIVE LOGITS

AddTagHelper

0.63

arusian

0.61

 <=",

0.60

styleType

0.54

mobileqq

0.53

IVAL

0.52

 للمعارف

0.52

ніципалі

0.51

 ddelweddau

0.51

}}}

0.50

Activations Density 0.800%

language about special education or disabilities

with

No Comments

No Known Activations