INDEX

Explanations

the open curly brace character "{"

oai_token-act-pair · gemini-2.0-flash

code and table data

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.64

-0.59

-0.57

-0.56

-0.54

-0.52

createTextNode

-0.50

↵↵

-0.50

POSITIVE LOGITS

 myſelf

1.02

 itſelf

0.93

 Jefus

0.89

 ſeveral

0.81

 himſelf

0.79

 depositphotos

0.78

 bershka

0.77

:✨

0.77

 Reſ

0.76

 censiti

0.76

Activations Density 0.500%

the open curly brace character "{"

code and table data

No Comments

No Known Activations