INDEX

Explanations

terms related to medical or technical software

oai_token-act-pair · gemini-2.0-flash

data, code, medical terms

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

URLException

-0.92

 myſelf

-0.85

 pleaſure

-0.84

DockStyle

-0.84

 ſmall

-0.84

Efq

-0.84

 greateſt

-0.83

 الرياضيه

-0.82

GEBURTSDATUM

-0.82

 ſeveral

-0.82

POSITIVE LOGITS

 notes

0.56

Ar

0.56

im

0.51

 note

0.50

 Char

0.50

Im

0.47

 Notes

0.47

Con

0.46

eventName

0.46

 Note

0.45

Activations Density 2.277%

terms related to medical or technical software

data, code, medical terms

No Comments

No Known Activations