INDEX

Explanations

words about efficient use of resources

oai_token-act-pair · gemini-2.0-flash

use

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

QMetaType

-0.71

ThroughAttribute

-0.68

 StatefulWidget

-0.65

 gynhyrchwyd

-0.65

oredCriteria

-0.63

########.

-0.62

 propOrder

-0.59

 OMITBAD

-0.59

الحياه

-0.57

verwijspagina

-0.56

POSITIVE LOGITS

use

1.81

 utilization

1.56

use

1.53

Use

1.50

Use

1.49

 utilisation

1.48

 utilize

1.48

 usage

1.45

 utilise

1.36

 uses

1.32

Activations Density 0.740%

words about efficient use of resources

use

No Comments

No Known Activations