INDEX

Explanations

law and legal-speak words such as voted, sanctions, policy

oai_token-act-pair · gemini-2.0-flash

against

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

yung

-0.50

ErrorException

-0.48

 paramString

-0.45

ARTER

-0.45

Errorf

-0.42

ż

-0.42

endphp

-0.41

#+#

-0.40

__()

-0.40

ORDAN

-0.39

POSITIVE LOGITS

 against

3.33

 Against

2.97

against

2.94

Against

2.89

 AGAINST

2.55

 contre

2.11

 gegen

1.99

 против

1.84

 tegen

1.70

 againſt

1.62

Activations Density 2.068%

law and legal-speak words such as voted, sanctions, policy

against

No Comments

No Known Activations