INDEX

Explanations

this neuron appears to find passages discussing the intersection of government policy, healthcare, and energy/corporate interests.

oai_token-act-pair · gemini-2.0-flash

Social and medical issues

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 Theſe

-0.82

 raiſ

-0.77

 myſelf

-0.69

Eſ

-0.69

 Anſ

-0.67

 uſed

-0.66

 Monfieur

-0.66

 theſe

-0.65

 fhew

-0.65



-0.65

POSITIVE LOGITS

Geplaatst

0.53

acc

0.52

funeralhome

0.49

0.47

ApiException

0.46

0.44

꿔

0.43

calibur

0.42

less

0.42

뀔

0.42

Activations Density 5.128%

this neuron appears to find passages discussing the intersection of government policy, healthcare, and energy/corporate interests.

Social and medical issues

No Comments

No Known Activations