INDEX

Explanations

words and punctuation that are part of technical writing

oai_token-act-pair · gemini-2.0-flash

punctuation

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

-0.83

 pleaſure

-0.56

 themſelves

-0.47

 neceſſ

-0.46

 Theſe

-0.46

 myſelf

-0.46

 Chriftian

-0.45

 reaſon

-0.44

 theſe

-0.44

oubtedly

-0.43

POSITIVE LOGITS

tagHelperRunner

1.21

rungsseite

0.65

TagHelpers

0.64

__(/*!

0.63

abestanden

0.63

MemoryWarning

0.63

 Normdatei

0.62

 revés

0.62

Datuak

0.62

 BorderSide

0.62

Activations Density 16.620%

words and punctuation that are part of technical writing

punctuation

No Comments

No Known Activations