INDEX

Explanations

prepositions next to verbs

oai_token-act-pair · gemini-2.0-flash

to

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

Története

-0.71

SourceChecksum

-0.66

 bezeichneter

-0.66

WriteTagHelper

-0.64

 nakalista

-0.61

 judiciaire

-0.60

 >=",

-0.60

chauffer

-0.60

ViewImports

-0.58

AddTagHelper

-0.58

POSITIVE LOGITS

 تضيفلها

0.58

 surla

0.52

SEB

0.49

 intermediate

0.48

esc

0.47

drop

0.46

 виправивши

0.45

Espèce

0.44

rem

0.44

Activations Density 1.167%

prepositions next to verbs

to

No Comments

No Known Activations