INDEX

Explanations

words related to data collection, scientific reports, and studies.

oai_token-act-pair · gemini-2.0-flash

organization

np_max-act-logits · 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

'{@

-0.64

RenderAtEndOf

-0.63

MigrationBuilder

-0.60

 arranged

-0.59

 organised

-0.56

HideFlags

-0.53

 organized

-0.53

kulum

-0.52

 Arranged

-0.51

 coordinated

-0.49

POSITIVE LOGITS

 organization

2.50

 organisation

2.38

 Organization

2.08

 Organisation

1.98

organization

1.95

Organization

1.92

 ORGANIZATION

1.91

organisation

1.77

 organisatie

1.75

 organización

1.72

Activations Density 7.922%

words related to data collection, scientific reports, and studies.

organization

No Comments

No Known Activations