INDEX

Explanations

the word "So"

oai_token-act-pair · gemini-2.0-flash

So

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

so

-1.09

So

-0.90

so

-0.89

så

-0.82

So

-0.81

 так

-0.78

 così

-0.71

 כך

-0.70

如此

-0.65

SO

-0.59

POSITIVE LOGITS

SharedDtor

0.75

AndroidJUnit

0.63

CloseOperation

0.62

 does

0.62

expandindo

0.59

 Paglinawan

0.58

انجليز

0.57

 BitmapFactory

0.57

SerializeField

0.57

did

0.56

Activations Density 0.338%

the word "So"

So

No Comments

No Known Activations