INDEX

Explanations

conditional statements with "or."

oai_token-act-pair · gemini-2.0-flash

or

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

and

-1.20

or

-1.16

and

-0.82

-0.71

↵

-0.71

<eos>

-0.71

-0.70

or

-0.69

And

-0.67

POSITIVE LOGITS

StoryboardSegue

1.70

 myſelf

1.63

Efq

1.63

 Monfieur

1.60

 Normdatei

1.52

RenderAtEndOf

1.45

 itſelf

1.42

 ―――――

1.41

 تضيفلها

1.40

 ſeveral

1.40

Activations Density 13.175%

conditional statements with "or."

or

No Known Activations

conditional statements with "or."

or

No Known Activations