INDEX

Explanations

code snippets with references to elements of programming languages

oai_token-act-pair · gemini-2.0-flash

next, last, first

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

hmig

-0.54

echt

-0.54

mybatisplus

-0.48

émie

-0.47

 Dupont

-0.44

wpi

-0.42

 uParam

-0.40

wyneth

-0.40

bertson

-0.40

achsen

-0.40

POSITIVE LOGITS

 समीक्षाओं

0.82

GEBURTSDATUM

0.78

 चीज़ों

0.75

InjectAttribute

0.69

SourceChecksum

0.69

 المعيارى

0.65

msgTypes

0.65

رشف

0.65

setVerticalGroup

0.63

NameInMap

0.63

Activations Density 3.283%

code snippets with references to elements of programming languages

next, last, first

No Comments

No Known Activations