INDEX

Explanations

language related to recipes and cooking

oai_token-act-pair · gemini-2.0-flash

oil or fat

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Oil

-0.78

Oil

-0.76

oil

-0.76

OIL

-0.74

oil

-0.71

 ujednoznacz

-0.69

contentLoaded

-0.68

 olje

-0.67

 Oils

-0.65

 يتيمه

-0.65

POSITIVE LOGITS

ViewFeatures

0.47

 Kirke

0.46

XXI

0.44

postMessage

0.43

lon

0.43

]?.

0.43

Whew

0.42

 незавершена

0.40

AppMethodBeat

0.40

[['

0.39

Activations Density 4.527%

language related to recipes and cooking

oil or fat

No Comments

No Known Activations