INDEX

Explanations

first person pronouns and language about video production or filmmaking

oai_token-act-pair · gemini-2.0-flash

editing

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

DockStyle

-0.80

 ExecuteAsync

-0.79

setVerticalGroup

-0.76

ChildScrollView

-0.75

webElementXpaths

-0.74

InjectAttribute

-0.71

 StatelessWidget

-0.69

 MainAxisSize

-0.69

StructEnd

-0.69

enderror

-0.68

POSITIVE LOGITS

 editing

1.31

 edit

1.27

 edited

1.12

edit

1.11

 Editing

1.06

Edit

1.05

 Edit

1.05

EDIT

0.99

Editing

0.98

 post

0.96

Activations Density 1.170%

first person pronouns and language about video production or filmmaking

editing

No Comments

No Known Activations