INDEX

Explanations

code snippets including column names related to date and the word to

oai_token-act-pair · gemini-2.0-flash

to

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

rungsseite

-0.83

fjspx

-0.79

ScopeManager

-0.77

 الرياضيه

-0.71

 مواليد

-0.71

økt

-0.67

 calldata

-0.66

ContentAlignment

-0.66

SequentialGroup

-0.65

BeginContext

-0.64

POSITIVE LOGITS

 Egli

0.62

 sánchez

0.49

 Rimini

0.47

 Pingback

0.47

 abſ

0.45

 indipendente

0.45

 Cæsar

0.44

LSM

0.44

 Dauphin

0.44

"")

0.43

Activations Density 2.265%

code snippets including column names related to date and the word to

to

No Comments

No Known Activations