INDEX

Explanations

words that are related to bad or mysterious things.

oai_token-act-pair · gemini-2.0-flash

dominate

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

PhysRevLett

-0.52

 cherchés

-0.48

 ROSS

-0.47

틴

-0.45

 ross

-0.45

TextAppearance

-0.45

ziehung

-0.45

mì

-0.44

Ligações

-0.43

Old

-0.43

POSITIVE LOGITS

 dominant

1.48

 dominate

1.45

dominant

1.42

domin

1.41

 predominate

1.35

 dominates

1.34

 predominant

1.30

 abound

1.29

 dominance

1.26

 DOMIN

1.26

Activations Density 2.668%

words that are related to bad or mysterious things.

dominate

No Comments

No Known Activations