INDEX

Explanations

code-related language and error messages

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_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 تعدى

-0.57

grunns

-0.56

]}>

-0.52

webElement

-0.49

WRP

-0.49

TestingModule

-0.49

MigrationBuilder

-0.47

はじめに

-0.47

 Вікі

-0.47

wakili

-0.46

POSITIVE LOGITS

IntoConstraints

0.75

󠁢

0.63

DockStyle

0.58

HideFlags

0.57

Espèce

0.57

extAlignment

0.55

vlog

0.54

asher

0.53

HostException

0.52

UVWXYZ

0.52

Activations Density 2.640%

code-related language and error messages

Code and errors

No Comments

No Known Activations