INDEX

Explanations

legal language describing purpose, intent, and testimony

oai_token-act-pair · gemini-2.0-flash

intend

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 réflex

-0.46

 Spartans

-0.43

 أعلام

-0.42

/~

-0.41

 hoff

-0.41

 Domini

-0.40

jov

-0.40

 lightest

-0.40

 nearest

-0.40

 Velo

-0.40

POSITIVE LOGITS

writeFieldEnd

0.75

PMailer

0.74

 FetchType

0.65

 NSCoder

0.65

ValueGeneration

0.64

 protoimpl

0.62

PRNewswire

0.61

AddTagHelper

0.61

μβρίου

0.60

richTextPanel

0.60

Activations Density 6.324%

legal language describing purpose, intent, and testimony

intend

No Comments

No Known Activations