INDEX

Explanations

words and phrases related to research, technical, and scientific topics.

oai_token-act-pair · gemini-2.0-flash

forum posts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 EClass

-0.49

 års

-0.45

 shoot

-0.44

pyx

-0.43

踏み

-0.42

indon

-0.41

WebElementEntity

-0.41

 yıld

-0.41

djangoproject

-0.41

ดด

-0.41

POSITIVE LOGITS

aarrggbb

0.96

 CreateTagHelper

0.81

]='\

0.69

findpost

0.68

DoubleQuotes

0.65

')")

0.63

Tracce

0.62

 AssemblyCompany

0.62

Tikang

0.61

 '\\;'

0.61

Activations Density 3.522%

words and phrases related to research, technical, and scientific topics.

forum posts

No Comments

No Known Activations