INDEX

Explanations

words and phrases related to business strategies and/or limitations

oai_token-act-pair · gemini-2.0-flash

Report excerpts

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

id

-0.53

 pouss

-0.48

ējās

-0.46

ates

-0.45

endforeach

-0.45

 strada

-0.44

work

-0.44

 AppBundle

-0.44

Chorus

-0.44

ucid

-0.43

POSITIVE LOGITS

enumi

0.65

 становника

0.63

PreferredItem

0.63

 resourceCulture

0.60

saraba

0.59

 silo

0.58

AsUp

0.58

DockStyle

0.58

bufio

0.57

 waterfall

0.57

Activations Density 3.432%

words and phrases related to business strategies and/or limitations

Report excerpts

No Comments

No Known Activations