INDEX

Explanations

text related to leadership positions and providing feedback

oai_token-act-pair · gemini-2.0-flash

management

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

væ

-0.47

ństwa

-0.46

会員

-0.45

مصادر

-0.44

toHave

-0.44

ˎ

-0.43

 keempat

-0.42

낙

-0.42

iecie

-0.42

usercontent

-0.42

POSITIVE LOGITS

 management

1.65

 managers

1.54

management

1.48

 manager

1.46

 Management

1.46

Management

1.38

 Managers

1.36

 managerial

1.33

manager

1.29

managers

1.29

Activations Density 2.328%

text related to leadership positions and providing feedback

management

No Comments

No Known Activations