INDEX

Explanations

language related to negotiation or policy, or car operation

oai_token-act-pair · 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

 task

-0.65

 Aufgabe

-0.61

LabelTagHelper

-0.57

AndroidJUnit

-0.57

DockStyle

-0.54

dafx

-0.53

DrawerToggle

-0.52

πον

-0.52

iculous

-0.52

 تضيفلها

-0.51

POSITIVE LOGITS

:✨

0.66

InvalidProtocol

0.60

клопе

0.56

 jScrollPane

0.56

RenderAtEndOf

0.55

 theory

0.55

 arşivlendi

0.54

 befolk

0.53

 fleet

0.52

 lccn

0.52

Activations Density 10.221%

language related to negotiation or policy, or car operation

No Comments

No Known Activations