INDEX

Explanations

the word "under".

oai_token-act-pair · gemini-2.0-flash

under

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

 under

-0.58

beginPath

-0.56

ArgsConstructor

-0.55

Under

-0.55

 Under

-0.55

 JComboBox

-0.54

 Bulan

-0.52

BuilderFactory

-0.52

science

-0.50

BagConstraints

-0.49

POSITIVE LOGITS

 kasarigan

0.61

SizeF

0.59

Datuak

0.58

 &___

0.52

 >=",

0.51

 jScrollPane

0.50

ImageContext

0.50

 سكانية

0.50

CodeDom

0.50

adpleegd

0.50

Activations Density 0.445%

the word "under".

under

No Comments

No Known Activations