INDEX

Explanations

geographic locations having to do with the train/metro

oai_token-act-pair · gemini-2.0-flash

old French honorifics

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

ar

-0.42

="#"><

-0.41

ko

-0.40

 Star

-0.40

)):

-0.40

tak

-0.40

go

-0.40

 Taylor

-0.40

)))

-0.40

رز

-0.40

POSITIVE LOGITS

 Monfieur

1.24

Efq

1.15

 ſeveral

1.09

 itſelf

1.09

 Majefty

1.06

 Theſe

1.05

 poffible

1.02

 pleaſure

1.01

 leaſt

1.00

 myſelf

0.99

Activations Density 18.628%

geographic locations having to do with the train/metro

old French honorifics

No Comments

No Known Activations