INDEX

Explanations

java code

oai_token-act-pair · gemini-2.0-flash

code, file paths

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

 Kirke

-0.50

 effetto

-0.48

useNewUrlParser

-0.45

AllAfrica

-0.44

:✨

-0.43

hysema

-0.42

LEncoder

-0.40

 Tijuana

-0.40

Mär

-0.40

 suffixes

-0.39

POSITIVE LOGITS

 autorytatywna

0.83

 فريبيس

0.76

richTextPanel

0.74

0.68

complexContent

0.65

 estekak

0.65

 utafitiHapana

0.65

ApiModel

0.64

 ویکی‌پدی

0.62

WriteTagHelper

0.62

Activations Density 0.843%

java code

code, file paths

No Comments

No Known Activations