INDEX

Explanations

phrases indicating the existence of options.

oai_token-act-pair · gemini-2.0-flash

something

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

GEBURTSDATUM

-0.94

 препратки

-0.75

 fieldNum

-0.73

 nahilalakip

-0.70

 autorytatywna

-0.69

LookAnd

-0.69

 nakalista

-0.68

SequentialGroup

-0.66

Parcelize

-0.66

 Spisak

-0.66

POSITIVE LOGITS

 something

1.89

something

1.66

Something

1.63

 Something

1.60

 SOMETHING

1.22

 quelque

1.17

 somethin

1.13

 algo

1.10

 något

1.09

 coś

1.09

Activations Density 0.583%

phrases indicating the existence of options.

something

No Comments

No Known Activations