INDEX

Explanations

numbers and dates in various contexts

oai_token-act-pair · gemini-2.0-flash

identifiers, codes

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

 varandra

-0.60

 automatiques

-0.58

 démocr

-0.57

 enfans

-0.54

 religieuses

-0.54

 sauvages

-0.54

 avoient

-0.54

 nationaux

-0.53

 réguli

-0.52

 prêtres

-0.52

POSITIVE LOGITS

 ་་

0.60

 nahilalakip

0.57

MigrationBuilder

0.54

 Roskov

0.54

InjectAttribute

0.53

ECR

0.52

 photolibrary

0.51

IFT

0.51

 AssemblyProduct

0.50

CTP

0.50

Activations Density 31.660%

numbers and dates in various contexts

identifiers, codes

No Comments

No Known Activations