INDEX

Explanations

concepts related to a code and converting across different languages.

oai_token-act-pair · gemini-2.0-flash

Focus, direction

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

Personensuche

-1.32

 الحره

-1.12

fjspx

-1.00

 المعيارى

-0.99

SourceChecksum

-0.96

 betweenstory

-0.91

rungsseite

-0.90

findpost

-0.90

 estekak

-0.89

 Majefty

-0.86

POSITIVE LOGITS

<bos>

0.68

0.46

 said

0.46

0.43

0.40

 cease

0.39

 across

0.38

in

0.37

Activations Density 3.432%

concepts related to a code and converting across different languages.

Focus, direction

No Comments

No Known Activations