INDEX

Explanations

words or phrases related to legal or historical context

oai_token-act-pair · gemini-2.0-flash

had

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 TestBed

-0.68

 tartalomajánló

-0.66

adaptiveStyles

-0.63

uxxxx

-0.59

 Wiktionnaire

-0.57

 WaitForSeconds

-0.52

 ExecuteAsync

-0.52

ಿದೆ

-0.51

__*/

-0.50

oznam

-0.49

POSITIVE LOGITS

had

2.83

Had

2.55

had

2.50

Had

2.48

HAD

1.98

HAD

1.63

 avaient

1.56

 hatten

1.55

 hatte

1.54

 habían

1.51

Activations Density 5.362%

words or phrases related to legal or historical context

had

No Comments

No Known Activations