INDEX

Explanations

phrases referencing future actions or steps

oai_token-act-pair · gemini-2.0-flash

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

]--;

-0.44

 guarn

-0.43

 henvisninger

-0.43

スタンド

-0.41

lja

-0.40

ance

-0.40

 raso

-0.39

zA

-0.38

 Four

-0.38

мени

-0.38

POSITIVE LOGITS

 next

3.03

next

2.69

Next

2.50

 Next

2.39

 NEXT

2.14

NEXT

2.02

 nächsten

1.95

 nächste

1.90

 nästa

1.88

 næste

1.80

Activations Density 1.029%

phrases referencing future actions or steps

next

No Comments

No Known Activations