INDEX

Explanations

positive recommendations

oai_token-act-pair · gemini-2.0-flash

recommend

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 poffe

-0.69

xFFFFFFFF

-0.66

 autorytatywna

-0.63

 ftate

-0.63

stdc

-0.60

 whoſe

-0.60

InvalidProtocol

-0.60

 utafitiHapana

-0.59

TintMode

-0.58

ειτουργ

-0.58

POSITIVE LOGITS

 CreateTagHelper

0.56

 sepen

0.49

eseorang

0.47

 Carrot

0.46

arankan

0.46

EndGlobalSection

0.45

 dedo

0.45

 Dear

0.45

.(*

0.45

 Pointer

0.45

Activations Density 0.277%

positive recommendations

recommend

No Comments

No Known Activations