INDEX

Explanations

words related to science, scientists, and research

oai_token-act-pair · gemini-2.0-flash

scientist/inventor

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

Gön

-0.56

ANEOUS

-0.53

UnusedPrivate

-0.53

tonsoft

-0.52

LookAnd

-0.51

ORIAL

-0.50

máscara

-0.47

찮

-0.47

 ends

-0.47

ContentAsync

-0.46

POSITIVE LOGITS

gameserver

0.67

/>";

0.56

antart

0.56

}{*}{}

0.56

">${

0.55

PhysRev

0.55

 />';

0.55

 jPanel

0.54

createStatement

0.54

 NSObject

0.54

Activations Density 4.332%

words related to science, scientists, and research

scientist/inventor

No Comments

No Known Activations