INDEX

Explanations

descriptions of people and things that are somewhat positive

oai_token-act-pair · gemini-2.0-flash

the

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

SharedDtor

-0.61

thâu

-0.58

reactstrap

-0.56

FXML

-0.52

)]);

-0.50

!*\

-0.49

ItemBackground

-0.48

참고

-0.48

ⓧ

-0.47

 TextAppearance

-0.46

POSITIVE LOGITS

 highly

0.85

highly

0.77

 extremely

0.70

 excellent

0.69

 wonderful

0.66

 lovely

0.63

 excelente

0.62

 excellently

0.62

the

0.61

 wonderfully

0.61

Activations Density 0.906%

descriptions of people and things that are somewhat positive

the

No Comments

No Known Activations