INDEX

Explanations

large numbers, often including non-numeric characters

oai_token-act-pair · gemini-2.0-flash

zero

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

<bos>

-1.09

kháu

-0.48

bootstrapcdn

-0.47

 arrivo

-0.40

-0.39

orteur

-0.38

the

-0.38

WithIOException

-0.37

findpost

-0.37

to

-0.36

POSITIVE LOGITS

CppMethod

0.77

ButterKnife

0.70

 Volga

0.69

++)

0.68

 ſeveral

0.67

 degeneracy

0.66

 sulphide

0.65

 Neighbourhood

0.64

sidemargin

0.64

 Avalanche

0.63

Activations Density 1.936%

large numbers, often including non-numeric characters

zero

No Comments

No Known Activations