INDEX

Explanations

section headers, figure captions, and comments pertaining to data or files

oai_token-act-pair · gemini-2.0-flash

technical writing

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

 Bourgoin

-0.82

ItemBackground

-0.70

 '\\;'

-0.69

 فريبيس

-0.68

saraba

-0.68

ChildScrollView

-0.65

+#+#

-0.63

исленность

-0.59

PyExc

-0.59

HasAnnotation

-0.58

POSITIVE LOGITS

下载附件

0.47

 Canadá

0.45

 ratusan

0.44

Interment

0.42

кульп

0.41

zené

0.41

wszy

0.41

 město

0.40

WireFormatLite

0.40

 menawarkan

0.40

Activations Density 0.666%

section headers, figure captions, and comments pertaining to data or files

technical writing

No Comments

No Known Activations