INDEX

Explanations

words related to using a computer

oai_token-act-pair · gemini-2.0-flash

technical jargon or code

np_token-act-pair-logits · gemini-2.0-flash

coding

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

<bos>

-0.48

↵↵

-0.46

Up

-0.45

richTextPanel

-0.44

UP

-0.44

rrggbb

-0.44

style

-0.43

Демографія

-0.43

utilisons

-0.43

obtain

-0.42

POSITIVE LOGITS

 تانيه

0.77

 يتيمه

0.72

BufferException

0.67

]='\

0.66

 FileReader

0.63

 muualla

0.63

horabuena

0.63

Vaata

0.63

getDoctrine

0.63

 IndexPath

0.62

Activations Density 2.463%

words related to using a computer

technical jargon or code

coding

No Comments

No Known Activations