INDEX

Explanations

a complex combination of words and short phrases, often involving an attempt to understand something being discussed.

oai_token-act-pair · gemini-2.0-flash

properly

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

Enllaces

-0.50

 Вікіпе

-0.48

bleau

-0.46

VersionUID

-0.45

)|^{

-0.43

breos

-0.43

 nakalista

-0.42

AndEndTag

-0.42

pierw

-0.42

iterable

-0.41

POSITIVE LOGITS

 properly

1.68

 proper

1.65

Proper

1.55

proper

1.54

 correctly

1.52

 PROPER

1.52

 Proper

1.51

properly

1.49

 correct

1.47

 Properly

1.45

Activations Density 2.702%

a complex combination of words and short phrases, often involving an attempt to understand something being discussed.

properly

No Comments

No Known Activations