INDEX

Explanations

abbreviations, numbers, and chemical formulas

oai_token-act-pair · gemini-2.0-flash

code/identifiers

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

StructEnd

-0.68

RefNanny

-0.59

addCriterion

-0.56

setVerticalGroup

-0.55

 EconPapers

-0.52

 orar

-0.52

IonicModule

-0.51

SBATCH

-0.49

BASEPATH

-0.49

ClCompile

-0.47

POSITIVE LOGITS

MigrationBuilder

0.52

falgar

0.52

 Toussaint

0.49

 Teng

0.49

rz

0.48

 Faso

0.48

liz

0.47

בוצ

0.46

tamol

0.45

rija

0.45

Activations Density 2.370%

abbreviations, numbers, and chemical formulas

code/identifiers

No Comments

No Known Activations