INDEX

Explanations

the word "mouse" when used in a computing or trapping context

oai_token-act-pair · gemini-2.0-flash

Mouse studies

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 mouse

-1.97

rat

-1.88

 Mouse

-1.86

 rats

-1.83

 mice

-1.70

Mouse

-1.70

mouse

-1.66

Rat

-1.64

 Rats

-1.62

 Mice

-1.59

POSITIVE LOGITS

 Aker

0.50

 <>",

0.49

jspx

0.47

 Sert

0.46

 Smyrna

0.46

FormTagHelper

0.46

extAlignment

0.46

Crom

0.46

şil

0.45

σμα

0.45

Activations Density 2.821%

the word "mouse" when used in a computing or trapping context

Mouse studies

No Comments

No Known Activations