INDEX

Explanations

acronyms in parentheses with some terms slightly weighted more than others

oai_token-act-pair · gemini-2.0-flash

Abbreviations and acronyms

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

ima

-0.59

inga

-0.58

mergeFrom

-0.55

OMA

-0.55

IMA

-0.55

ULA

-0.54

zula

-0.54

IIA

-0.54

 ExecuteAsync

-0.54

DebuggerNonUser

-0.53

POSITIVE LOGITS

 propOrder

0.56

xsi

0.52

atschappij

0.52

principalTable

0.51

PI

0.51

sekten

0.48

FI

0.46

či

0.45

 Numerade

0.45

fi

0.45

Activations Density 1.382%

acronyms in parentheses with some terms slightly weighted more than others

Abbreviations and acronyms

No Comments

No Known Activations