INDEX

Explanations

words related to physical and mental wellbeing, sometimes in the context of social connection

oai_token-act-pair · gemini-2.0-flash

line

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

withstanding

-1.42

theless

-1.34

ization

-1.31

queous

-1.21

neath

-1.17

time

-1.17

imed

-1.16

ergies

-1.16

poptosis

-1.16

fraid

-1.15

POSITIVE LOGITS

ponym

0.57

multirow

0.55

stø

0.53

 disambiguazione

0.52

umpang

0.50

 giuri

0.50

året

0.49

hofer

0.49

skab

0.48

 stør

0.48

Activations Density 1.460%

words related to physical and mental wellbeing, sometimes in the context of social connection

line

No Comments

No Known Activations