INDEX

Explanations

scientific publication citations

oai_token-act-pair · gemini-2.0-flash

Scientific/legal citations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

GHIJKLM

-0.57

HasForeignKey

-0.56

 oprot

-0.53

masin

-0.53

 Meilleur

-0.53

hopped

-0.53

posedge

-0.52

uality

-0.52

olites

-0.52

 Regular

-0.51

POSITIVE LOGITS

 Infórmanos

0.59

Liefs

0.49

 thôi

0.48

Atsauces

0.48

 generali

0.46

اعمال

0.45

 prêtre

0.43

 pinulongan

0.43

 AllAfrica

0.41

 začet

0.41

Activations Density 0.832%

scientific publication citations

Scientific/legal citations

No Comments

No Known Activations