INDEX

Explanations

SQL database related terms, especially when discussing encoding and specifications

oai_token-act-pair · gemini-2.0-flash

Database queries/management

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

 database

-2.03

DB

-2.00

db

-1.97

 Database

-1.95

DB

-1.89

Database

-1.84

db

-1.83

Db

-1.80

database

-1.77

 databases

-1.76

POSITIVE LOGITS

vstack

0.56

 roux

0.49

 NSCoder

0.49

 Gele

0.48

ticale

0.48

cyd

0.47

 chuyến

0.47

 uintptr

0.46

impulan

0.45

allage

0.45

Activations Density 1.115%

SQL database related terms, especially when discussing encoding and specifications

Database queries/management

No Comments

No Known Activations