INDEX

Explanations

code snippets and certain keywords related to programming

oai_token-act-pair · gemini-2.0-flash

printing

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

PhysRevD

-0.49

BeginContext

-0.48

်း

-0.46

stateMutability

-0.45

nestjs

-0.44

 Vorles

-0.44

idste

-0.44

 Clement

-0.44

 تضيفلها

-0.43

CodedInputStream

-0.42

POSITIVE LOGITS

 print

0.80

 printing

0.78

 Print

0.76

 PRINT

0.76

 prints

0.75

 PRINTING

0.69

UnusedPrivate

0.68

 Printing

0.67

 printed

0.66

prints

0.66

Activations Density 4.056%

code snippets and certain keywords related to programming

printing

No Comments

No Known Activations