INDEX

Explanations

verbs and words that can be verbs

oai_token-act-pair · gemini-2.0-flash

foreign languages

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

AND

-0.85

ंड

-0.84

und

-0.84

UND

-0.81

ND

-0.80

nd

-0.79

undur

-0.77

undo

-0.75

ण्ड

-0.75

nd

-0.74

POSITIVE LOGITS

Slf

0.68

комо

0.62

 ویکی‌پدی

0.60

 kasarigan

0.57

 للاسماء

0.55

 الحره

0.54

 Jacobsen

0.53

pisah

0.53

 AssemblyCulture

0.52

 AssemblyVersion

0.52

Activations Density 3.095%

verbs and words that can be verbs

foreign languages

No Comments

No Known Activations