INDEX

Explanations

a word that is associated with collections of things, such as numbers, families (genes, members) or groups

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 family

-2.66

family

-2.34

Family

-2.22

 Family

-2.17

 FAMILY

-2.03

FAMILY

-1.88

 famille

-1.62

 famiglia

-1.58

 Familie

-1.54

 família

-1.48

POSITIVE LOGITS

:✨

0.58

 باخ

0.57

Климат

0.51

Impressum

0.44

hibe

0.43

Tembelea

0.42

seamnă

0.42

Vaata

0.41

Affiliation

0.41

getItemId

0.41

Activations Density 6.215%

a word that is associated with collections of things, such as numbers, families (genes, members) or groups

No Comments

No Known Activations