INDEX

Explanations

code snippets and diagrams that use specific notation and terminology, possibly related to linear algebra or data representation.

oai_token-act-pair · gemini-2.0-flash

thick solid

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

olí

-0.47

migrationBuilder

-0.44

 venido

-0.42

 paio

-0.41

Now

-0.41

 قاد

-0.41

>();

-0.40

λευτα

-0.39

<?>>

-0.39

Now

-0.39

POSITIVE LOGITS

 propOrder

0.86

ftagPool

0.85

 المعيارى

0.82

InjectAttribute

0.81

 الاطلاع

0.69

 صوتيه

0.67

المكان

0.67

fromnode

0.65

\{\\

0.65

uesia

0.64

Activations Density 19.165%

code snippets and diagrams that use specific notation and terminology, possibly related to linear algebra or data representation.

thick solid

No Comments

No Known Activations