INDEX

Explanations

words and phrases related to psychotherapy

oai_token-act-pair · gemini-2.0-flash

government, systems, policy

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

 FetchType

-0.85

الحياه

-0.81

 TestBed

-0.81

+#+#

-0.77

 transférez

-0.74

 StatefulWidget

-0.66

ModelSerializer

-0.65

labelledby

-0.63

 विश्वसनीयता

-0.63

″]

-0.63

POSITIVE LOGITS

 sector

0.60

íncia

0.52

 SECTOR

0.51

 Sector

0.50

Sector

0.50

SECTOR

0.49

zeug

0.49

 secteurs

0.48

варь

0.47

sector

0.46

Activations Density 0.925%

words and phrases related to psychotherapy

government, systems, policy

No Comments

No Known Activations