INDEX

Explanations

vocabulary related to blood testing and analysis

oai_token-act-pair · gemini-2.0-flash

technical reports

np_token-act-pair-logits · gemini-2.0-flash

blood samples, lab specimens

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

HostException

-0.65

 виправивши

-0.59

Efq

-0.58

izr

-0.58

 Jefus

-0.56

 '\\;'

-0.54

 protoimpl

-0.53

 AdapterView

-0.52

ModelState

-0.51

 myſelf

-0.50

POSITIVE LOGITS

 useCallback

0.55

헌

0.52

DispatchToProps

0.49

 veau

0.49

 nhiệt

0.49

ული

0.45

lesias

0.45

asten

0.45

 marca

0.43

)}^{

0.43

Activations Density 2.213%

vocabulary related to blood testing and analysis

technical reports

blood samples, lab specimens

No Comments

No Known Activations