INDEX

Explanations

code snippets including regular expressions and Django or web server code

oai_token-act-pair · gemini-2.0-flash

code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

terase

-0.72

 AssemblyVersion

-0.66

lgari

-0.66

dotenv

-0.58

AccessorTable

-0.57

NewUrlParser

-0.57

Datuak

-0.55

 Winaray

-0.52

PreferredItem

-0.52

=$?

-0.52

POSITIVE LOGITS

 jScrollPane

0.59

 amitié

0.56

Clik

0.53

يكب

0.53

σχ

0.52

 classiques

0.46

humble

0.46

 proposées

0.46

Примі

0.46

RELATED

0.45

Activations Density 3.657%

code snippets including regular expressions and Django or web server code

code

No Comments

No Known Activations