INDEX

Explanations

quantity expressions which are formatted as "for/in/of the last X"

oai_token-act-pair · gemini-2.0-flash

the

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 next

-2.47

next

-2.30

Next

-2.22

 Next

-2.11

 NEXT

-1.84

NEXT

-1.76

 nächste

-1.65

 nächsten

-1.61

 próximo

-1.42

 prochaine

-1.37

POSITIVE LOGITS

 later

0.52

 last

0.49

 yesterday

0.43

 späteren

0.43

 letzt

0.42

 últimos

0.41

lor

0.40

vė

0.40

lichen

0.39

las

0.39

Activations Density 1.839%

quantity expressions which are formatted as "for/in/of the last X"

the

No Comments

No Known Activations