INDEX

Explanations

mentions of years, especially those in the 1900s

oai_token-act-pair · gemini-2.0-flash

0

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 äta

-0.48

Спољашње

-0.44

vaadin

-0.42

waitKey

-0.42

 vandens

-0.40

 wolle

-0.40

 GetComponent

-0.40

را

-0.40

 sonriendo

-0.40

 aufmerksam

-0.40

POSITIVE LOGITS

 يتيمه

0.67

 arşivlendi

0.63

ագրություններ

0.62

Autoritní

0.59

oredCriteria

0.56

 ujednoznacz

0.54

✨:

0.53

 للمعارف

0.53

ptonshire

0.53

ьаж

0.52

Activations Density 3.497%

mentions of years, especially those in the 1900s

0

No Comments

No Known Activations