INDEX

Explanations

numbers with "3" in them, sometimes followed by special characters like "%" or "-D"

oai_token-act-pair · gemini-2.0-flash

3

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

tagHelperRunner

-0.57

 bezeichneter

-0.56

aculture

-0.56

ૃ

-0.53

adpleegd

-0.52

 Rook

-0.50

Bit

-0.50

Karakteristik

-0.49

beth

-0.49

Zurück

-0.49

POSITIVE LOGITS

ViewImports

0.63

ArgsConstructor

0.60

حوالہ

0.56

prnewswire

0.56

 GenerationType

0.56

Datuak

0.56

ConstraintMaker

0.56

Olympia

0.55

 GridLayout

0.54

DockStyle

0.53

Activations Density 2.252%

numbers with "3" in them, sometimes followed by special characters like "%" or "-D"

3

No Comments

No Known Activations