INDEX

Explanations

content related to time or places, possibly from news articles

oai_token-act-pair · gemini-2.0-flash

days of the week

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 aikana

-0.53

 enää

-0.48

 määrä

-0.46

 meille

-0.45

 doccia

-0.43

 capucha

-0.42

 rhestr

-0.42

 piele

-0.42

corrente

-0.41

 huidige

-0.41

POSITIVE LOGITS

 yesterday

2.02

 Saturday

2.02

 Monday

1.96

 Friday

1.94

 Tuesday

1.93

 Thursday

1.92

 Wednesday

1.91

 Sunday

1.83

Saturday

1.70

 Yesterday

1.69

Activations Density 1.568%

content related to time or places, possibly from news articles

days of the week

No Comments

No Known Activations