INDEX

Explanations

words related to probability, especially regarding health

oai_token-act-pair · gemini-2.0-flash

Increased

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

 chances

-0.77

 chance

-0.75

 Chances

-0.73

expandindo

-0.70

AxisAlignment

-0.69

chance

-0.68

 probability

-0.68

 CreateTagHelper

-0.66

AndroidJUnit

-0.65

########.

-0.64

POSITIVE LOGITS

 increased

1.51

 increase

1.51

 Increased

1.45

 increases

1.43

 Increases

1.38

 Increase

1.38

increase

1.38

Increased

1.35

Increase

1.34

increased

1.34

Activations Density 1.220%

words related to probability, especially regarding health

Increased

No Comments

No Known Activations