INDEX

Explanations

words relating to disparate technical or policy topics

oai_token-act-pair · gemini-2.0-flash

words that start with P

np_token-act-pair-logits · gemini-2.0-flash

random words in context

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

Datuak

-0.70

libft

-0.69

 &___

-0.66

 nahilalakip

-0.65

saraba

-0.65

 समीक्षक

-0.65

 propOrder

-0.63

WebElementEntity

-0.63

ftagPool

-0.63

 ***!

-0.61

POSITIVE LOGITS

 Peep

0.47

 Picking

0.46

 picking

0.45

 peep

0.44

 carreteras

0.43

 dře

0.42

Picking

0.41

 mitään

0.41

Shout

0.41

 piernas

0.41

Activations Density 4.501%

words relating to disparate technical or policy topics

words that start with P

random words in context

No Comments

No Known Activations