INDEX

Explanations

fairly common words that often appear in scientific or technical writing

oai_token-act-pair · gemini-2.0-flash

technical descriptions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

AddTagHelper

-0.57

 ***!

-0.49

:✨

-0.49

不如

-0.46

 peup

-0.44

ToProps

-0.44

 Collegiate

-0.44

 éta

-0.44

 Organ

-0.44

 prefi

-0.43

POSITIVE LOGITS

Παραπομπές

0.80

Fordítás

0.71

 Normdatei

0.62

 autorytatywna

0.60

Референце

0.60

viewWillAppear

0.59

Tikang

0.56

istoitu

0.56

>");

0.54

SuppressMessage

0.53

Activations Density 0.649%

fairly common words that often appear in scientific or technical writing

technical descriptions

No Comments

No Known Activations