INDEX

Explanations

the abbreviation for minutes ("min") when it refers to a duration of time in an exercise or experimental context.

oai_token-act-pair · gemini-2.0-flash

min

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

min

-1.36

min

-1.08

Min

-1.02

Min

-0.98

...

-0.93

-0.79

 minimum

-0.77

-0.73

the

-0.71

POSITIVE LOGITS

 Monfieur

1.77

 myſelf

1.73

Efq

1.70

 Majefty

1.63

 Houſe

1.59

 houſe

1.56

 Theſe

1.49

 Jefus

1.46

 becauſe

1.46

 itſelf

1.45

Activations Density 0.720%

the abbreviation for minutes ("min") when it refers to a duration of time in an exercise or experimental context.

min

No Comments

No Known Activations