INDEX

Explanations

LaTeX code and mathematical expressions

oai_token-act-pair · gemini-2.0-flash

\[

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

ValueStyle

-0.70

Personensuche

-0.55

Termine

-0.55

ۜ

-0.53

 Ανακτήθηκε

-0.50

">//

-0.49

 magasiner

-0.48

ardless

-0.47

IonicModule

-0.46

~”

-0.46

POSITIVE LOGITS

BF

0.52

afp

0.51

bnf

0.51

BoxShadow

0.51

 nakalista

0.50

saraba

0.50

ranath

0.50

BAH

0.49

ayana

0.49

krishnan

0.49

Activations Density 8.655%

LaTeX code and mathematical expressions

\[

No Comments

No Known Activations