INDEX

Explanations

words related to relationships, family and personal experiences

oai_token-act-pair · gemini-2.0-flash

difficult, emotional experiences

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 Meksiku

-0.75

WindowConstants

-0.54

mein

-0.50

ListItemIcon

-0.50

Mech

-0.48

AntiForgeryToken

-0.48

DidLoad

-0.47

polizei

-0.47

Caution

-0.46

KommentareTeilen

-0.46

POSITIVE LOGITS

 married

0.63

 ExecuteAsync

0.60

rungsseite

0.57

帖最后由

0.57

ConstraintMaker

0.53

homonymie

0.53

LikeLike

0.52

 تعدى

0.51

Efq

0.51

CGRectMake

0.51

Activations Density 2.480%

words related to relationships, family and personal experiences

difficult, emotional experiences

No Comments

No Known Activations