INDEX

Explanations

Java/C++/C# code

oai_token-act-pair · gemini-2.0-flash

Code and errors

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ximately

-0.60

 CreateTagHelper

-0.59

)$\\

-0.56

vsky

-0.49

msgSender

-0.49

żą

-0.49

fible

-0.49

Bronnen

-0.48

انجليز

-0.48

”]

-0.47

POSITIVE LOGITS

TagMode

0.72

 tombé

0.59

 turística

0.58

PMailer

0.57

 يتيمه

0.57

 handker

0.57

VIAF

0.55

sekten

0.54

 houſe

0.54

 shawl

0.54

Activations Density 1.174%

Java/C++/C# code

Code and errors

No Comments

No Known Activations