INDEX

Explanations

content related to scientific publications or journals

oai_token-act-pair · gemini-2.0-flash

academic papers

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

contentLoaded

-0.91

 houſe

-0.90

Efq

-0.86

parsedMessage

-0.85

StoryboardSegue

-0.84

RenderAtEndOf

-0.83

WebVitals

-0.82

存于互联网档案馆

-0.82

MigrationBuilder

-0.82

 betweenstory

-0.81

POSITIVE LOGITS

 under

0.58

nem

0.51

0.49

th

0.48

ar

0.47

ent

0.47

 plan

0.47

Activations Density 1.362%

content related to scientific publications or journals

academic papers

No Comments

No Known Activations