INDEX

Explanations

words related to cosmetic procedures

oai_token-act-pair · gemini-2.0-flash

medical/cosmetic procedures

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

="{

-0.44

pwd

-0.43

 Abbé

-0.43

 Gewähr

-0.41

impinan

-0.41

NgModule

-0.41

 Tugas

-0.40

 Maroc

-0.40

contentLoaded

-0.40

 Metho

-0.40

POSITIVE LOGITS

miral

0.77

 Mere

0.57

 Treatments

0.57

AccessorTable

0.54

 treatments

0.54

FileDescriptor

0.53

Treating

0.52

rawDesc

0.52

archiviato

0.52

uxxxx

0.52

Activations Density 2.980%

words related to cosmetic procedures

medical/cosmetic procedures

No Comments

No Known Activations