INDEX

Explanations

code and other markup

oai_token-act-pair · gemini-2.0-flash

Code/Programming

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 const

-0.52

 Савезне

-0.52

-0.51

au

-0.49

-0.48

<code>

-0.48

cho

-0.47

duto

-0.46

view

-0.45

чої

-0.45

POSITIVE LOGITS

 ་་

0.82

 متعلقه

0.81

 doubtnut

0.68

 '\\;'

0.68

 itſelf

0.67

Personendaten

0.66

TagMode

0.66

 photolibrary

0.66

 nakalista

0.66

>",

0.65

Activations Density 0.207%

code and other markup

Code/Programming

No Comments

No Known Activations