INDEX

Explanations

the word "none", sometimes near "we" or "success"

oai_token-act-pair · gemini-2.0-flash

none

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

 varandra

-0.76

jména

-0.75

 frågan

-0.71

 محفوظة

-0.70

IsMutable

-0.69

 Atlántico

-0.67

 Staub

-0.66

 defenses

-0.66

 bäst

-0.65

󠁿

-0.65

POSITIVE LOGITS

 XCTest

0.63

expandindo

0.60

цезда

0.58

 onAnimation

0.58

 HomeController

0.55

Personensuche

0.54

uric

0.52

ra

0.52

 виправивши

0.51

enterOuterAlt

0.50

Activations Density 0.804%

the word "none", sometimes near "we" or "success"

none

No Comments

No Known Activations