INDEX

Explanations

code import statements, specifically "javax.ws.rs" and "java.util"

oai_token-act-pair · gemini-2.0-flash

code snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

lasi

-0.56

 Village

-0.53

MENAFN

-0.52

alt

-0.49

ớp

-0.48

 носи

-0.48

kär

-0.47

createCanvas

-0.47

leg

-0.47

POSITIVE LOGITS

 transfieras

0.69

 CreateTagHelper

0.67

الحياه

0.65

 незавершена

0.65

Kjelder

0.64

 חיצוניים

0.64

ArrowToggle

0.63

 ویکی‌پدیا

0.61

ſelf

0.59

OGND

0.59

Activations Density 0.441%

code import statements, specifically "javax.ws.rs" and "java.util"

code snippets

No Comments

No Known Activations