INDEX

Explanations

code and numerical sequences.

oai_token-act-pair · gemini-2.0-flash

Code segments

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-1.85

-0.70

-0.69

-0.59

-0.58

-0.55

-0.54

<strong>

-0.54

-0.50

-0.49

POSITIVE LOGITS

 ویکی‌پدیا

1.20

Попис

1.11

RegressionTest

1.09

 noDo

1.01

 دیکھیے

0.99

 Савезне

0.99

 unknownFields

0.98

Personendaten

0.97

UnusedPrivate

0.95

Diweddarwch

0.94

Activations Density 2.891%

code and numerical sequences.

Code segments

No Comments

No Known Activations