INDEX

Explanations

words related to video technology

oai_token-act-pair · gemini-2.0-flash

video content

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 audio

-0.64

 unknownFields

-0.57

 filmed

-0.54

 мѣ

-0.52

новништво

-0.51

 nakalista

-0.48

 camera

-0.48

 film

-0.48

 ویکی‌پدیا

-0.47

 AUDIO

-0.47

POSITIVE LOGITS

+#+#

0.67



0.63

lapsingToolbar

0.54

 ExecuteAsync

0.54

CSE

0.53

 Aerial

0.52

 Virtual

0.52

 soutient

0.51

DateString

0.49

VR

0.49

Activations Density 1.373%

words related to video technology

video content

No Comments

No Known Activations