INDEX

Explanations

categories and lists, often on web pages

oai_token-act-pair · gemini-2.0-flash

See/Also

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

-0.70

WithIOException

-0.64

-0.58

ázaro

-0.58

/*---

-0.58

StructEnd

-0.57

Kjelder

-0.57

-0.56

#,

-0.55

fony

-0.55

POSITIVE LOGITS

 also

1.11

Also

0.98

 Also

0.97

also

0.94

 related

0.83

Related

0.81

 Related

0.80

 también

0.79

 também

0.76

related

0.74

Activations Density 0.527%

categories and lists, often on web pages

See/Also

No Known Activations