INDEX

Explanations

mentions of medical research institutions, especially the city they're in

oai_token-act-pair · gemini-2.0-flash

Names and locations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للاسماء

-0.62

 виправивши

-0.60

 virš

-0.55

曖昧さ回避

-0.54

 AssemblyCulture

-0.50

Salta

-0.49

RSpec

-0.48

acuzzi

-0.47

jewództ

-0.47

uvwxyz

-0.47

POSITIVE LOGITS

 LIRE

0.54

 kriti

0.49

説

0.48

 Mith

0.47

 Prakash

0.47

 Perseus

0.46

 Dhar

0.46

uhn

0.45

 betweenstory

0.45

yog

0.44

Activations Density 0.877%

mentions of medical research institutions, especially the city they're in

Names and locations

No Comments

No Known Activations