INDEX

Explanations

names, titles and locations, particularly those followed by commas or numbers

oai_token-act-pair · gemini-2.0-flash

comma

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.52

↵↵

-0.41

jur

-0.40

<bos>

-0.40

-0.39

</

-0.39

--

-0.39

windowFixed

-0.39

///</

-0.38

POSITIVE LOGITS

 незавершена

0.84

^(@)

0.69

 Majefty

0.67

oforte

0.66

 مواليد

0.65

 vulgaires

0.65

 againſt

0.63

monary

0.62

énario

0.62

DockStyle

0.62

Activations Density 6.211%

names, titles and locations, particularly those followed by commas or numbers

comma

No Comments

No Known Activations