INDEX

Explanations

a variety of different tokens, but a few stand out: dates, numbers, and category labels

oai_token-act-pair · gemini-2.0-flash

Non-English/code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

at

-0.53

↵

-0.52

Not

-0.49

off

-0.48

At

-0.47

 early

-0.46

To

-0.45

So

-0.45

he

-0.44

POSITIVE LOGITS

 חיצוניים

0.75

__((

0.72

 ویکی‌پدیای

0.71

PerformLayout

0.71

 مرئيه

0.68

expandindo

0.68

abetes

0.66

SourceChecksum

0.65

 GenerationType

0.65

VersionUID

0.65

Activations Density 0.764%

a variety of different tokens, but a few stand out: dates, numbers, and category labels

Non-English/code

No Comments

No Known Activations