INDEX

Explanations

newspaper or media outlet names

oai_token-act-pair · gemini-2.0-flash

News articles

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 StatelessWidget

-0.69

setDo

-0.65

UnusedPrivate

-0.61

__).

-0.60

oredCriteria

-0.57

 désolés

-0.56

<?

-0.53

$__

-0.53

__;

-0.52

gonic

-0.51

POSITIVE LOGITS

tymologie

0.52

 Triangle

0.51

Cyfarwyddwr

0.49

 betweenstory

0.48

oa̍t

0.47

ieza

0.47

críbete

0.45

smithy

0.44

 chron

0.43

 Chron

0.42

Activations Density 0.269%

newspaper or media outlet names

News articles

No Comments

No Known Activations