INDEX

Explanations

examples of code snippets, as well as words that are related to coding like class and properties

oai_token-act-pair · gemini-2.0-flash

Code snippets and foreign words

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

-0.73

-0.68

-0.64

-0.62

-0.59

de

-0.58

-0.56

to

-0.55

as

-0.55

POSITIVE LOGITS

 Monfieur

1.57

Efq

1.47

 Houſe

1.35

 myſelf

1.34

 kasarigan

1.30

 Jefus

1.30

 Theſe

1.26

MigrationBuilder

1.26

 houſe

1.24

 Diſ

1.23

Activations Density 0.415%

examples of code snippets, as well as words that are related to coding like class and properties

Code snippets and foreign words

No Comments

No Known Activations