INDEX

Explanations

data presented in a table format, particularly data including numbers and symbols in a structured way

oai_token-act-pair · gemini-2.0-flash

|

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ModelExpression

-0.68

AddTagHelper

-0.65

 myſelf

-0.60

httphttps

-0.60

ſelf

-0.60

Efq

-0.60

 Jefus

-0.60

AddHtmlAttribute

-0.59

 photolibrary

-0.59

 auffi

-0.59

POSITIVE LOGITS

 communiquez

0.53

 ویکی‌پدی

0.51

 defaultstate

0.50

 getRule

0.48

razos

0.48

EndInit

0.47

DebuggerStep

0.46

 مشين

0.46

 endIndex

0.46

 consultato

0.45

Activations Density 38.162%

data presented in a table format, particularly data including numbers and symbols in a structured way

|

No Comments

No Known Activations