INDEX

Explanations

phrases involving "not" followed by a verb and time expressions like "until"

oai_token-act-pair · gemini-2.0-flash

time limit

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

esgue

-0.74

MLLoader

-0.73

ьажоргаш

-0.73

StackNavigator

-0.71

PerformLayout

-0.71

parsedMessage

-0.69

 الدولى

-0.69

 Normdatei

-0.68

HasForeignKey

-0.68

AccessorTable

-0.66

POSITIVE LOGITS

 until

2.59

until

2.27

 Until

2.17

Until

2.16

 UNTIL

2.05

 till

1.94

 untill

1.74

Till

1.61

 hasta

1.55

 TILL

1.54

Activations Density 2.702%

phrases involving "not" followed by a verb and time expressions like "until"

time limit

No Comments

No Known Activations