INDEX

Explanations

automotive engineering and design terminology

oai_token-act-pair · gemini-2.0-flash

car wheel position

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

'{@

-0.66

åt

-0.57

AutoresizingMask

-0.56

 Quad

-0.55

__]

-0.54

 quadruple

-0.53

 quad

-0.52

SJ

-0.52

 CanadaChoose

-0.52

stø

-0.52

POSITIVE LOGITS

ViewFeatures

0.47

انج

0.47

colgroup

0.47

UnitTesting

0.47

specifier

0.46

 الرياضيه

0.46

 engin

0.46

 muualla

0.45

Distinctions

0.45

 Vikipedi

0.45

Activations Density 0.427%

automotive engineering and design terminology

car wheel position

No Comments

No Known Activations