INDEX

Explanations

code snippets related to images and loops

oai_token-act-pair · gemini-2.0-flash

code/data

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

asantry

-0.52

Mem

-0.47

 Engaging

-0.46

raulic

-0.45

φαλ

-0.44

 sinusoidal

-0.44



-0.44

 unjust

-0.44

ruptive

-0.44

compliant

-0.44

POSITIVE LOGITS

 محفوظة

0.84

Personensuche

0.73

 ujednoznacz

0.68

GraphicsUnit

0.63

enumi

0.61

 courseId

0.61

 שוליים

0.60

 فريبيس

0.60

 viewDidLoad

0.59

tagext

0.59

Activations Density 21.747%

code snippets related to images and loops

code/data

No Comments

No Known Activations