INDEX

Explanations

Latex code related including images with captions

oai_token-act-pair · gemini-2.0-flash

LaTeX code

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

 tightness

-0.60

 Duda

-0.60

erráneo

-0.57

 Schweitzer

-0.56

 strerror

-0.54

aulted

-0.54

󠁢

-0.54

 mortos

-0.54

OwnerId

-0.54

 quenched

-0.54

POSITIVE LOGITS

ConstraintMaker

0.79

TagMode

0.73

SharedCtor

0.69

GEBURTSDATUM

0.69

HtmlAttribute

0.68

AntiForgeryToken

0.66

WriteBarrier

0.66

 &___

0.65

InjectAttribute

0.64

RetentionPolicy

0.63

Activations Density 1.982%

Latex code related including images with captions

LaTeX code

No Comments

No Known Activations