INDEX

Explanations

code snippets with keywords like class, private, public, stepper, data, and handler.

oai_token-act-pair · gemini-2.0-flash

Code/Data Structures

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

batore

-0.45

<bos>

-0.43

 Seitz

-0.40

ibrill

-0.38

ogi

-0.38

ık

-0.37

 вот

-0.37

 mẽ

-0.36

checs

-0.36

okie

-0.35

POSITIVE LOGITS

PerformLayout

0.69

SharedDtor

0.67

 ExecuteAsync

0.65

 Baillargeon

0.62

leſs

0.61

 odkazy

0.61

Portail

0.60

edn

0.60

EndInit

0.60

 HasFactory

0.60

Activations Density 12.014%

code snippets with keywords like class, private, public, stepper, data, and handler.

Code/Data Structures

No Comments

No Known Activations