INDEX

Explanations

historical or political texts related to conflict or disputes

oai_token-act-pair · gemini-2.0-flash

bold

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ComVisible

-0.74

 незавершена

-0.73

 فريبيس

-0.69

ArgsConstructor

-0.68

 saites

-0.64

 sociaux

-0.60

 InputDecoration

-0.60

 Deviant

-0.59

expandindo

-0.58

 resourceCulture

-0.58

POSITIVE LOGITS

ⓧ

0.55

glTranslatef

0.49

map

0.43

تاح

0.43

pshot

0.43

احة

0.43

期刊论文

0.42

num

0.41

 PLWABN

0.41

{}",

0.41

Activations Density 1.983%

historical or political texts related to conflict or disputes

bold

No Comments

No Known Activations