INDEX

Explanations

third-person references, code snippets, and references to research.

oai_token-act-pair · gemini-2.0-flash

code/technical documents

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

Three

-1.45

 Fourth

-1.44

Fourth

-1.43

 fourth

-1.42

 Three

-1.38

three

-1.32

fourth

-1.30

 three

-1.28

tri

-1.26

THREE

-1.22

POSITIVE LOGITS

 typelib

0.60

setupUi

0.60

ⓧ

0.59

INSEE

0.56

aluc

0.52

otoro

0.52

AutoModerator

0.52

strconv

0.51

NUK

0.51

uminen

0.50

Activations Density 1.962%

third-person references, code snippets, and references to research.

code/technical documents

No Comments

No Known Activations