INDEX

Explanations

scientific or mathematical expressions and terminology

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 uintptr

-0.73

 חיצוניים

-0.71

AndEndTag

-0.71

וויק

-0.68

 мәкал

-0.68

 समीक्षाएं

-0.62

awtextra

-0.61

Personendaten

-0.60

#+#

-0.60

 BytesLike

-0.60

POSITIVE LOGITS

реи

0.45

begle

0.44

abinieri

0.43

hilt

0.43

AutoresizingMask

0.42

appName

0.42

श्च

0.41

glieder

0.41

PONENT

0.40

digans

0.39

Activations Density 6.273%

scientific or mathematical expressions and terminology

No Comments

No Known Activations