INDEX

Explanations

numerical data and mathematical symbols

oai_token-act-pair · gemini-2.0-flash

Code and numbers

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

WriteTagHelper

-0.69

 <>",

-0.68

GeoNames

-0.52

PostExecute

-0.51

appointment

-0.51

ატ

-0.50

Gweler

-0.48

 biografias

-0.48

 viewWillAppear

-0.48

brates

-0.48

POSITIVE LOGITS

ViewFeatures

0.62

HtmlAttribute

0.60

bootstrapcdn

0.53

MessageTagHelper

0.51

LEncoder

0.51

 fortnight

0.51

 propOrder

0.50

LookAnd

0.49

 "..\..\

0.49

نیم

0.49

Activations Density 18.500%

numerical data and mathematical symbols

Code and numbers

No Comments

No Known Activations