INDEX

Explanations

places, especially in Spain including restaurants, cities, streets and attractions

oai_token-act-pair · gemini-2.0-flash

Spanish/Portuguese prepositions

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

Efq

-1.43

 Anſ

-1.27

ſelf

-1.26

 itſelf

-1.24

 Reſ

-1.20

 Monfieur

-1.20

 faſt

-1.19

 raiſ

-1.18

ſelves

-1.17

 ―――――

-1.17

POSITIVE LOGITS

de

0.81

del

0.78

0.68

Ch

0.60

di

0.57

Del

0.56

0.55

 dell

0.54

 delle

0.53

 della

0.52

Activations Density 0.737%

places, especially in Spain including restaurants, cities, streets and attractions

Spanish/Portuguese prepositions

No Comments

No Known Activations