INDEX

Explanations

the word "just"

oai_token-act-pair · gemini-2.0-flash

just

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 intptr

-0.63

Клуб

-0.52

BeginContext

-0.51

 ends

-0.50

 indirec

-0.46

 Club

-0.45

isma

-0.43

Joc

-0.43

*_

-0.43

свое

-0.43

POSITIVE LOGITS

 يتيمه

0.80

 disambiguazione

0.72

IVEREF

0.72

 समीक्षाओं

0.70

Hochspringen

0.66

jgl

0.66

horabuena

0.65



0.64

Personendaten

0.63

HomeAsUpEnabled

0.61

Activations Density 0.649%

the word "just"

just

No Comments

No Known Activations