INDEX

Explanations

code snippets with symbols present in many programming languages

oai_token-act-pair · gemini-2.0-flash

parentheses

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TagMode

-0.54

awtextra

-0.49

refour

-0.49

 Ceinture

-0.48

])));

-0.47

Erfolge

-0.47

lichung

-0.47

kháu

-0.46

anthes

-0.46

ORROW

-0.46

POSITIVE LOGITS

 дописавши

0.75

 ligiloj

0.63

 betweenstory

0.56

 Kini

0.54

Autoritní

0.51

MMM

0.49

ριο

0.48

 makeStyles

0.47

didSet

0.47

dn

0.47

Activations Density 32.787%

code snippets with symbols present in many programming languages

parentheses

No Comments

No Known Activations