INDEX

Explanations

the word "tissue"

oai_token-act-pair · gemini-2.0-flash

tissue

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

RectangleBorder

-0.92

OGND

-0.82

 étoient

-0.75

WebVitals

-0.74

 avoient

-0.73

AndEndTag

-0.71

kloped

-0.71

 auroit

-0.70

 varandra

-0.70

ChildScrollView

-0.70

POSITIVE LOGITS

↵↵

1.01

0.70

0.66

 consistently

0.63

 There

0.61

semantics

0.61

“

0.60

 fact

0.60

not

0.60

The

0.58

Activations Density 1.538%

the word "tissue"

tissue

No Comments

No Known Activations