INDEX

Explanations

proper nouns, particularly names of places and people

oai_token-act-pair · gemini-2.0-flash

Polish language

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 informée

-0.61

 kaarangay

-0.52

InstrumentedTest

-0.51

RUnlock

-0.47

]-->

-0.47

 TextInputType

-0.45

ContentAsync

-0.45

 OMITBAD

-0.44

 EconPapers

-0.44

 unknownFields

-0.44

POSITIVE LOGITS

ęty

0.63

nąć

0.62

 prie

0.56

ęć

0.56

czaj

0.54

ął

0.52

跟

0.51

ęcie

0.51

ng

0.50

zył

0.50

Activations Density 2.860%

proper nouns, particularly names of places and people

Polish language

No Comments

No Known Activations