INDEX

Explanations

lists within the text

oai_token-act-pair · gemini-2.0-flash

all

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Erişim

-0.55

простра

-0.44

 vPvB

-0.42

NegativeButton

-0.42

ätie

-0.40

 Sometimes

-0.39

Sometimes

-0.39

quartered

-0.39

krie

-0.38

Vidite

-0.38

POSITIVE LOGITS

all

2.30

all

1.73

ALL

1.63

 semua

1.59

 allemaal

1.48

 tutte

1.41

 всех

1.38

 모두

1.37

 semuanya

1.37

 todas

1.37

Activations Density 1.116%

lists within the text

all

No Comments

No Known Activations