INDEX

Explanations

descriptions or a summary of events

oai_token-act-pair · gemini-2.0-flash

foreign words

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 >=",

-0.71

RunAsync

-0.69

 '\\;'

-0.68

OpenHelper

-0.66

InvalidProtocol

-0.65

principalTable

-0.65

upol

-0.62

 uintptr

-0.61

 onAnimation

-0.61

]")]

-0.60

POSITIVE LOGITS

 alimentaires

0.54

 surla

0.46

 OMITTED

0.46

солю

0.45

 portátiles

0.43

脈

0.43

Kanpo

0.42

gebn

0.41

neuri

0.41

 udrž

0.41

Activations Density 9.194%

descriptions or a summary of events

foreign words

No Comments

No Known Activations