INDEX

Explanations

mathematical notation and terminology

oai_token-act-pair · gemini-2.0-flash

algebraic geometry

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

IsContent

-0.75

AndEndTag

-0.73

</caption>

-0.61

TagMode

-0.61

 <<<<<<<<<<<<<<

-0.60

клопе

-0.60

:],

-0.58

fördert

-0.55

utives

-0.53

 vivement

-0.53

POSITIVE LOGITS

Cordialement

0.48

 hermit

0.47

=$?

0.44

 जर

0.43

ERMIN

0.43

 Fests

0.43

 Houſe

0.42

FieldBuilder

0.42

 Determin

0.41

 Hermit

0.41

Activations Density 3.005%

mathematical notation and terminology

algebraic geometry

No Comments

No Known Activations