INDEX

Explanations

strings of words related to business company names followed by action

oai_token-act-pair · gemini-2.0-flash

say "to"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

まま

-0.50

:✨

-0.47

しまった

-0.47

in

-0.44

em

-0.43

ToUpper

-0.42

en

-0.41

toHaveBeenCalled

-0.41

OutOf

-0.40

aws

-0.40

POSITIVE LOGITS

 efforts

1.47

 effort

1.47

 Efforts

1.42

efforts

1.38

effort

1.38

 esfuerzos

1.25

 Effort

1.23

 تلاش

1.21

Effort

1.17

 esfuerzo

1.09

Activations Density 0.759%

strings of words related to business company names followed by action

say "to"

No Comments

No Known Activations