INDEX

Explanations

phrases related to reasoning or justification

oai_token-act-pair · gemini-2.0-flash

why/reason

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 pinion

-0.56

obt

-0.55

FieldBuilder

-0.55

 Propri

-0.54

Kariera

-0.54

SharedDtor

-0.54

ThemeOverlay

-0.54

 Roskov

-0.54

ylase

-0.53

 Propriet

-0.53

POSITIVE LOGITS

ContentAsync

0.54

 lenker

0.48

הערות

0.48

apimachinery

0.48

onActivityResult

0.47

 MainAxisSize

0.46

ρων

0.46

 pinulongan

0.45

sizeCache

0.45

 CreateTagHelper

0.45

Activations Density 0.213%

phrases related to reasoning or justification

why/reason

No Comments

No Known Activations