INDEX

Explanations

prepositions and prepositional phrases.

oai_token-act-pair · gemini-2.0-flash

technical writing

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 ComVisible

-0.49

 yoksa

-0.45

參考文獻

-0.44

させる

-0.38

-0.37

-0.36

assertEqual

-0.35

POSITIVE LOGITS

 purpoſe

0.94

 disambiguazione

0.94

StoreMessageInfo

0.93

تقاوى

0.88

 houſe

0.85

 protoimpl

0.83

 Italijanski

0.83

Jereo

0.81

neſs

0.77

iffance

0.75

Activations Density 11.040%

prepositions and prepositional phrases.

technical writing

No Comments

No Known Activations