INDEX

Explanations

the word "on"

oai_token-act-pair · gemini-2.0-flash

on

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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>

-1.00

WithIOException

-0.67

}}}}

-0.67

 متعلقه

-0.66

utilisons

-0.65

tagHelperRunner

-0.64

principalTable

-0.63

__':

-0.63

'></

-0.61

 unknownFields

-0.61

POSITIVE LOGITS

 onOptions

0.66

 disambiguazione

0.50

 MatDialog

0.49

Tempor

0.46

ОК

0.45

 Tempor

0.45

 Baruch

0.44

 Helf

0.44

 collaborator

0.44

 Teas

0.43

Activations Density 0.536%

the word "on"

on

No Comments

No Known Activations