INDEX

Explanations

code snippets, particularly function and class declarations or uses of the keyword "return".

oai_token-act-pair · gemini-2.0-flash

code identifiers

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

="";

-0.54

DrawerToggle

-0.53

"])

-0.51

=?";

-0.51

)");

-0.50

='';

-0.50

]),

-0.49

spyOn

-0.48

")]

-0.47

RTEE

-0.47

POSITIVE LOGITS

 eventId

0.78

 courseId

0.77

 companyId

0.75

 postId

0.75

 createdBy

0.75

 roleId

0.74

 projectId

0.73

 orderId

0.71

 userRepository

0.70

 categoryId

0.70

Activations Density 1.783%

code snippets, particularly function and class declarations or uses of the keyword "return".

code identifiers

No Comments

No Known Activations