INDEX

Explanations

code snippets in JSON format

oai_token-act-pair · gemini-2.0-flash

{

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

</strong>

-0.85

-0.79

↵↵

-0.78

the

-0.75

<eos>

-0.75

↵

-0.73

</em>

-0.72

↵↵↵

-0.69

-0.68

<strong>

-0.67

POSITIVE LOGITS

styleType

1.66

parsedMessage

1.62

 مشين

1.59

DockStyle

1.56

AddTagHelper

1.55

 ModelExpression

1.55

 betweenstory

1.52

 autorytatywna

1.50

 tartalomajánló

1.48

setVerticalGroup

1.48

Activations Density 1.461%

code snippets in JSON format

{

No Comments

No Known Activations