INDEX

Explanations

the word "Gold" followed by other words

oai_token-act-pair · gemini-2.0-flash

gold

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

blue

-0.51

 blue

-0.47

 down

-0.47

 Yellow

-0.44

Blue

-0.44

MathML

-0.44

 fär

-0.43

 abenço

-0.43

 Magenta

-0.42

 BLUE

-0.41

POSITIVE LOGITS

MLLoader

0.72

Tikang

0.71

ArgumentParser

0.70

 unknownFields

0.70

findpost

0.65

derry

0.64

__.__

0.64

calaure

0.63

IBarButtonItem

0.63

 nakalista

0.62

Activations Density 1.731%

the word "Gold" followed by other words

gold

No Comments

No Known Activations