INDEX

Explanations

words indicating a scientific result or finding

oai_token-act-pair · gemini-2.0-flash

technical language

np_token-act-pair-logits · gemini-2.0-flash

Technical or academic texts

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

GTCX

-0.62

addCriterion

-0.61

ความ

-0.58

MLLoader

-0.50

ddha

-0.47

 auss

-0.47

 المعيارى

-0.46

 McCa

-0.46

istö

-0.46

SuccessListener

-0.46

POSITIVE LOGITS

:✨

0.57

ípio

0.56

verwijspagina

0.52

rungsseite

0.51

 theſe

0.49

Efq

0.49

TemporalType

0.49

참고

0.48

NDL

0.48

 ImportError

0.47

Activations Density 1.536%

words indicating a scientific result or finding

technical language

Technical or academic texts

No Comments

No Known Activations