INDEX

Explanations

a wide variety of domain specific terminology depending on other words in the snippet

oai_token-act-pair · gemini-2.0-flash

situation

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

 nahilalakip

-1.18

 AssemblyCompany

-1.05

featureID

-1.00

 '\\;'

-1.00

تقاوى

-0.98

NameInMap

-0.95

 &___

-0.94

 المعيارى

-0.93

GEBURTSDATUM

-0.91

astify

-0.90

POSITIVE LOGITS

 situation

0.62

 multitude

0.59

 scenario

0.53

 portion

0.45

 standpoint

0.45

 combination

0.44

 paradigm

0.44

 relationship

0.43

 copy

0.43

 thing

0.43

Activations Density 7.359%

a wide variety of domain specific terminology depending on other words in the snippet

situation

No Comments

No Known Activations