INDEX

Explanations

job advertisements targeted at or mentioning people

oai_token-act-pair · gemini-2.0-flash

Code/programming related text

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

-2.38

-2.06

-1.78

-1.70

wh

-1.65

wi

-1.57

wa

-1.56

WH

-1.53

Ｗ

-1.41

wl

-1.40

POSITIVE LOGITS

MergeFrom

0.59

 przód

0.55

 dieß

0.50

 słoń

0.49

</tfoot>

0.46

 fédéral

0.46

jątk

0.45

 pewno

0.44

 męski

0.44

 omge

0.44

Activations Density 10.479%

job advertisements targeted at or mentioning people

Code/programming related text

No Comments

No Known Activations