INDEX

Explanations

words related to code or a website

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 resourceCulture

-0.76

:✨

-0.76

 OFDb

-0.68

AndEndTag

-0.68

 autorytatywna

-0.65

 correctes

-0.61

 firmy

-0.60

 místa

-0.60

Kariera

-0.60

 Ressources

-0.60

POSITIVE LOGITS

glomer

0.51

licant

0.49

Ruj

0.49

creatic

0.48

FBS

0.47

 Deux

0.46

saw

0.46

[])

0.46

parseDouble

0.45

raised

0.45

Activations Density 1.922%

words related to code or a website

No Comments

No Known Activations