INDEX

Explanations

terms and locations related to medical care and litigation

oai_token-act-pair · gemini-2.0-flash

therapy/rehabilitation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ंदीखरीदारी

-0.71

눠

-0.60

 linkovi

-0.60

asuring

-0.55

Hochspringen

-0.55

 auffi

-0.55

 ainfi

-0.55

서는

-0.55

 Theſe

-0.55

 AssemblyVersion

-0.54

POSITIVE LOGITS

}></

0.57

#![

0.55

 pinulongan

0.50

 chi̍t

0.49

цтва

0.48

MethodManager

0.47

୧

0.46

WaitGroup

0.44

انيف

0.43

XmlEnum

0.43

Activations Density 1.114%

terms and locations related to medical care and litigation

therapy/rehabilitation

No Comments

No Known Activations