INDEX

Explanations

references to personal experiences and self-discovery, particularly related to finding purpose and overcoming adversity.

oai_token-act-pair · gemini-2.0-flash

"in" in other languages

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

 life

-0.95

 فريبيس

-0.84

rawDesc

-0.77

life

-0.77

Life

-0.76

 Life

-0.75

 LIFE

-0.69

 lenker

-0.68

LIFE

-0.68

 snippetHide

-0.68

POSITIVE LOGITS

in

1.52

 dalam

0.91

ใน

0.90

 trong

0.83

в

0.82

în

0.79

 في

0.78

 nella

0.73

 در

0.71

 فى

0.64

Activations Density 1.809%

references to personal experiences and self-discovery, particularly related to finding purpose and overcoming adversity.

"in" in other languages

No Comments

No Known Activations