INDEX

Explanations

code snippets, file names, and directory names

oai_token-act-pair · gemini-2.0-flash

code and logs

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 itſelf

-0.90

$_"

-0.89

 crdi

-0.88

 pleaſure

-0.86

 raiſ

-0.86

 uſed

-0.86

 elettrica

-0.85

 myſelf

-0.84

 ―――――

-0.82

 Jefus

-0.81

POSITIVE LOGITS

0.57

0.54

0.49

 super

0.48

0.47

0.46

“

0.45

0.44

et

0.43

Activations Density 7.529%

code snippets, file names, and directory names

code and logs

No Comments

No Known Activations