INDEX

Explanations

words that join parts of sentences together

oai_token-act-pair · gemini-2.0-flash

Sentence fragments

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

ButterKnife

-0.54

ArgsConstructor

-0.51

롯

-0.50

 oídos

-0.49

 &___

-0.48

addPreferredGap

-0.47

reportWebVitals

-0.47

SceneManagement

-0.47

 numberWith

-0.46

GenerationType

-0.46

POSITIVE LOGITS

Personensuche

0.61

 myſelf

0.54

InjectAttribute

0.52

contentLoaded

0.52

 Planned

0.51

tronic

0.50

findpost

0.49

脚注の使い方

0.49

 dieß

0.48

 متعلقه

0.48

Activations Density 1.777%

words that join parts of sentences together

Sentence fragments

No Comments

No Known Activations