INDEX

Explanations

a combination of numbers, statistics and some proper nouns

oai_token-act-pair · gemini-2.0-flash

numerical data

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

 виправивши

-0.64

انيف

-0.63

featureID

-0.61

 getopt

-0.60

MigrationBuilder

-0.59

 TextInputType

-0.59

 PLWABN

-0.58

WireFormatLite

-0.58

ISupport

-0.58

protoc

-0.57

POSITIVE LOGITS

 sauvages

0.25

 commerciaux

0.24

 automatiques

0.24

 espagne

0.24

 nationaux

0.23

 enfans

0.23

 vectorielles

0.22

 avoient

0.22

 quæ

0.21

 religieuses

0.21

Activations Density 9.178%

a combination of numbers, statistics and some proper nouns

numerical data

No Comments

No Known Activations