INDEX

Explanations

occurrences of the word "work" or "works."

oai_token-act-pair · gemini-2.0-flash

work

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Hentet

-0.55

 zufolge

-0.54

ScopeManager

-0.53

WithMany

-0.52

+#+

-0.51

URLException

-0.50

marginVertical

-0.50

ⓧ

-0.49

 estime

-0.48

 लेकर

-0.48

POSITIVE LOGITS

 autorytatywna

0.68

 विश्वसनीयता

0.65

usermodel

0.63

 ProtoMessage

0.62

Przeczytaj

0.60

 مشين

0.59

piecze

0.58

WithIOException

0.58

 candela

0.57

 ampoule

0.57

Activations Density 0.153%

occurrences of the word "work" or "works."

work

No Comments

No Known Activations