INDEX

Explanations

LaTeX code

oai_token-act-pair · gemini-2.0-flash

special symbols and formatting in documents

np_token-act-pair-logits · gpt-4o-mini

\

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 gyhoeddwyd

-0.57

+:+

-0.56

PageModule

-0.52

 blouses

-0.52

sie

-0.50

ьаж

-0.49

模

-0.49

гло

-0.49

 verily

-0.48

brü

-0.48

POSITIVE LOGITS

 resourceCulture

0.66

ChildScrollView

0.66

IntoConstraints

0.62

 disambiguazione

0.60

 дописавши

0.54

HasForeignKey

0.54

 كومونز

0.53

醐

0.53

%",

0.51

InputBorder

0.50

Activations Density 4.043%

LaTeX code

special symbols and formatting in documents

\

No Comments

No Known Activations