INDEX

Explanations

terms related to writing, typography, and editing

oai_token-act-pair · gemini-2.0-flash

writing and editing

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GeneratedMessage

-0.62

xFFFFFFFF

-0.60

ⓧ

-0.60

WriteTagHelper

-0.59

 Realt

-0.59

mobileqq

-0.59

parsedMessage

-0.58

AddTagHelper

-0.57

ymce

-0.57

 Turki

-0.56

POSITIVE LOGITS

<bos>

0.75

ConstraintMaker

0.66

Réponse

0.50

دانشنامهٔ

0.48

 précisé

0.46

)")

0.42

 незавершена

0.42

 vote

0.42

IBar

0.42

 enregist

0.42

Activations Density 2.153%

terms related to writing, typography, and editing

writing and editing

No Comments

No Known Activations