INDEX

Explanations

words/phrases indicating direction or movement

oai_token-act-pair · gemini-2.0-flash

House locations

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

AxisAlignment

-0.56

 ModelExpression

-0.53

 AssemblyProduct

-0.51

 américains

-0.50

pendente

-0.47

 sayap

-0.47

HasAnnotation

-0.47

外部連結

-0.46

 BoxFit

-0.45

Населення

-0.45

POSITIVE LOGITS

expandindo

0.65

 tartalomajánló

0.64

Tembelea

0.60

]")]

0.60

 door

0.57

ignment

0.57

 متعلقه

0.56

 يتيمه

0.56

egrave

0.56

euse

0.56

Activations Density 0.712%

words/phrases indicating direction or movement

House locations

No Comments

No Known Activations