INDEX

Explanations

latex formatting language

oai_token-act-pair · gemini-2.0-flash

{

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

jsii

-0.59

UnsafeEnabled

-0.55

 snippetHide

-0.54

 ProtoMessage

-0.52

().__

-0.51

InjectAttribute

-0.50

::$_

-0.49

 EClass

-0.49

#+#

-0.48

classnames

-0.47

POSITIVE LOGITS

ormais

0.66

 vectorielle

0.61

licazione

0.59

 altrimenti

0.53

likace

0.53

 conosco

0.53

couvrir

0.51

醐

0.50

 Zeug

0.50

 mengangg

0.50

Activations Density 0.611%

latex formatting language

{

No Comments

No Known Activations