INDEX

Explanations

scientific formulas and mathematical expressions

oai_token-act-pair · gemini-2.0-flash

2

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

 pinulongan

-0.98

 AssemblyCulture

-0.85

InputBorder

-0.82

ंदीखरीदारी

-0.82

 дописавши

-0.81

StructEnd

-0.81

 مشين

-0.79

 itſelf

-0.79

Efq

-0.78

 >=",

-0.78

POSITIVE LOGITS

 null

0.46

 finally

0.43

setw

0.42

才

0.40

 free

0.40

 mang

0.40

既

0.39

kem

0.39

het

0.39

ява

0.39

Activations Density 30.128%

scientific formulas and mathematical expressions

2

No Comments

No Known Activations