INDEX

Explanations

words, symbols, and phrases common to mathematical or scientific writing.

oai_token-act-pair · gemini-2.0-flash

scientific/mathematical conditions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-0.99

↵

-0.93

-0.86

-0.76

↵↵

-0.74

“

-0.72

in

-0.71

-0.70

-0.68

POSITIVE LOGITS

 myſelf

1.40

 Jefus

1.35

 purpoſe

1.34

 greateſt

1.30

 Majefty

1.30

 itſelf

1.27

 Anſ

1.26

 beſt

1.25

 houſe

1.24

 Houſe

1.24

Activations Density 6.652%

words, symbols, and phrases common to mathematical or scientific writing.

scientific/mathematical conditions

No Comments

No Known Activations