INDEX

Explanations

places where quantities or numbers are mentioned

oai_token-act-pair · gemini-2.0-flash

quantities and estimation

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

 several

-1.13

 ſeveral

-1.11

 numerous

-1.09

 feveral

-1.07

 multiple

-1.05

several

-1.04

 many

-0.99

 Numerous

-0.95

Numerous

-0.95

 countless

-0.94

POSITIVE LOGITS

illoma

0.50

paravant

0.46

webElementXpaths

0.44

irnov

0.43

//{

0.39

']);

0.39

ModelAttribute

0.39

hånd

0.39

 Вікі

0.39

djangoproject

0.39

Activations Density 0.472%

places where quantities or numbers are mentioned

quantities and estimation

No Comments

No Known Activations