INDEX

Explanations

words related to science, religion, and faith

oai_token-act-pair · gemini-2.0-flash

theoretical/philosophical/scientific texts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 виправивши

-0.63

PreferredItem

-0.60

HtmlAttribute

-0.54

UnsafeEnabled

-0.53

TestingModule

-0.53

Portale

-0.51

RoutingModule

-0.51

 XNUMX

-0.48

 Италијани

-0.47

󠁢

-0.47

POSITIVE LOGITS

 resourceCulture

0.65

Viited

0.62

Kjelder

0.59

onChanged

0.59

 consent

0.54

MENAFN

0.53

 consenti

0.53

ver

0.52

 muualla

0.52

brock

0.51

Activations Density 3.190%

words related to science, religion, and faith

theoretical/philosophical/scientific texts

No Comments

No Known Activations