INDEX

Explanations

years represented with numerals

oai_token-act-pair · gemini-2.0-flash

2

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 beginnetje

-0.71

ⓧ

-0.56

 مشين

-0.55

=$?

-0.55

 disponibilités

-0.54

ształ

-0.54

$_['

-0.53

 protoimpl

-0.50

 soñ

-0.50

 nôtre

-0.50

POSITIVE LOGITS

UnsafeEnabled

0.48

dia

0.46

ye

0.46

ya

0.45

0.43

rrggbb

0.43

TLR

0.43

himovic

0.42

נטרנט

0.41

 Distrikt

0.41

Activations Density 5.104%

years represented with numerals

2

No Comments

No Known Activations