INDEX

Explanations

words and abbreviations pertaining to RNA viruses and the mechanisms through which they replicate

oai_token-act-pair · gemini-2.0-flash

RNA viruses

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

enumi

-0.86

KommentareTeilen

-0.86

Personensuche

-0.84

MessageOf

-0.79

HomeAsUpEnabled

-0.78

ArgsConstructor

-0.76

GEBURTSDATUM

-0.75

 Мексичка

-0.74

StoryboardSegue

-0.73

setVerticalGroup

-0.72

POSITIVE LOGITS

 BoxFit

0.44

COUVER

0.42

 source

0.40

 néz

0.40

kontroll

0.39

 permission

0.38

 manager

0.37

ate

0.36

дента

0.35

Activations Density 2.853%

words and abbreviations pertaining to RNA viruses and the mechanisms through which they replicate

RNA viruses

No Comments

No Known Activations