INDEX

Explanations

code snippets or programming-related discussions in multiple languages.

oai_token-act-pair · gemini-2.0-flash

programming code and errors

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

 Theſe

-0.63

 GoogleFonts

-0.55

 TAMBÉM

-0.54

 Bucure

-0.50

vailable

-0.49

Vorteile

-0.48

Efq

-0.48

 humanas

-0.48

 Monfieur

-0.47

 himſelf

-0.47

POSITIVE LOGITS

her

1.20

her

0.82

 الحره

0.69

Her

0.69

 متعلقه

0.66

Her

0.63

gameserver

0.60

badlogic

0.55

بوابة

0.53

portál

0.53

Activations Density 1.191%

code snippets or programming-related discussions in multiple languages.

programming code and errors

No Comments

No Known Activations