INDEX

Explanations

words related to appliances and machinery, especially features and specifications

oai_token-act-pair · gemini-2.0-flash

product specifications

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

PerformLayout

-0.88

 propOrder

-0.87

 initComponents

-0.79

 demografica

-0.76

DeleteBehavior

-0.71

verifyException

-0.69

AccessorTable

-0.69

AndEndTag

-0.68

مصادر

-0.68

 defaultstate

-0.67

POSITIVE LOGITS

 four

0.48

0.47

0.45

 electronic

0.45

two

0.44

 кӀ

0.42

 digital

0.42

 aluminum

0.42

led

0.41

 chip

0.41

Activations Density 3.624%

words related to appliances and machinery, especially features and specifications

product specifications

No Comments

No Known Activations