INDEX

Explanations

words related to places and transportation

oai_token-act-pair · gemini-2.0-flash

downtown

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 activado

-0.52

 Roskov

-0.52

ASSERT

-0.48

piram

-0.48

odetic

-0.48

 Halb

-0.46

Jîn

-0.46

 cromo

-0.46

わりに

-0.45

yc

-0.45

POSITIVE LOGITS

 المعيارى

0.76

NUMX

0.66

 iconFacebook

0.60

MemoryWarning

0.60

PositiveButton

0.57

//

0.57

########.

0.56

 cherchés

0.54

 INTERESAR

0.54

esterday

0.53

Activations Density 2.633%

words related to places and transportation

downtown

No Comments

No Known Activations