INDEX

Explanations

mathematical expressions

oai_token-act-pair · gemini-2.0-flash

Number 2 in brackets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

cm

-0.74

cm

-0.73

 inch

-0.70

 centimeter

-0.69

inch

-0.69

 centimetres

-0.68

 centi

-0.66

 centimeters

-0.65

 санти

-0.64

centi

-0.59

POSITIVE LOGITS

webElement

0.71

 hashCode

0.58

Portale

0.57

fjspx

0.55

+#+#

0.53

NameInMap

0.51

èbre

0.47

InjectAttribute

0.47

WireFormatLite

0.47

lapsingToolbar

0.46

Activations Density 0.940%

mathematical expressions

Number 2 in brackets

No Comments

No Known Activations