INDEX

Explanations

mathematical LaTex and related code, alongside some Spanish words

oai_token-act-pair · gemini-2.0-flash

code and math

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

una

-0.57

las

-0.51

ya

-0.47

sin

-0.45

con

-0.45

 mismo

-0.44

el

-0.43

 más

-0.43

 tiempo

-0.42

POSITIVE LOGITS

 ModelExpression

0.64

ływ

0.63

 esternos

0.63

 pinulongan

0.60

 Arabs

0.58

 Krakowie

0.58

 Não

0.57

não

0.57

 dissatisfaction

0.57

 Zweiten

0.57

Activations Density 4.730%

mathematical LaTex and related code, alongside some Spanish words

code and math

No Comments

No Known Activations