INDEX

Explanations

confidence intervals

oai_token-act-pair · gemini-2.0-flash

Confidence intervals

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

-1.78

 nine

-1.35

 ninety

-1.22

 Nine

-1.21

 ninth

-1.15

 Ninth

-1.13

九

-1.08

 nueve

-1.07

 NINE

-1.06

９

-1.06

POSITIVE LOGITS

StoreMessageInfo

0.68

Geplaatst

0.67

Datuak

0.63

 Normdatei

0.61

rawDesc

0.59

hassee

0.59

WithIOException

0.59

mybatisplus

0.58

rungsseite

0.57

chre

0.57

Activations Density 1.396%

confidence intervals

Confidence intervals

No Comments

No Known Activations