INDEX

Explanations

instances of the word 'Read' followed by the word 'More' or 'our' or 'review'

oai_token-act-pair · gemini-2.0-flash

Read

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

PreferredItem

-0.66

 läs

-0.54

 '\\;'

-0.50

TagMode

-0.48

Out

-0.48

read

-0.47

ьаж

-0.45

ISLAM

-0.45

RSS

-0.45

 Infórmanos

-0.44

POSITIVE LOGITS

 PyLong

0.74

ANDUM

0.63

 متعلقه

0.63

Enllaces

0.59

 дописавши

0.56

 تضيفلها

0.56

хьтан

0.54

@"/

0.54

 HasFactory

0.54

enegger

0.54

Activations Density 0.308%

instances of the word 'Read' followed by the word 'More' or 'our' or 'review'

Read

No Comments

No Known Activations