INDEX

Explanations

parts of addresses, specifically in the United States

oai_token-act-pair · gemini-2.0-flash

addresses

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LookAnd

-0.82

HideFlags

-0.61

Composable

-0.60

 TestBed

-0.59

rxjs

-0.59

########.

-0.57

{{/

-0.56

GeneratedMessage

-0.56

ecore

-0.56

UseVisualStyle

-0.55

POSITIVE LOGITS

hoben

0.53

 EconPapers

0.47

bootstrapcdn

0.45

 sportive

0.44

thenes

0.43

bit

0.43

PyExc

0.42

 strtotime

0.41

threaded

0.41

ahr

0.40

Activations Density 8.030%

parts of addresses, specifically in the United States

addresses

No Comments

No Known Activations