INDEX

Explanations

parts of words.

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 ErrIntOverflow

-0.80

 autorytatywna

-0.75

Personensuche

-0.65

 cherchés

-0.59

 мәкал

-0.58

Controllo

-0.57

figsize

-0.56

oredCriteria

-0.56

 disambiguazione

-0.56

Geplaatst

-0.55

POSITIVE LOGITS

 createState

0.55

]-->

0.54

ReusableCell

0.52

photobucket

0.51

دانشنامهٔ

0.48

InstanceState

0.47

BeginContext

0.47

odore

0.46

político

0.46

++]

0.44

Activations Density 3.767%

parts of words.

No Comments

No Known Activations