INDEX

Explanations

code snippets particularly with coordinate transformations or image processing functions

oai_token-act-pair · gemini-2.0-flash

isempty

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 itſelf

-1.51

 myſelf

-1.49

 pleaſure

-1.25

 Monfieur

-1.24

 ſtate

-1.24

 Jefus

-1.22

 Theſe

-1.21

 ſeveral

-1.21

 purpoſe

-1.20

 Houſe

-1.17

POSITIVE LOGITS

 nargin

0.91

 varargin

0.73

(:,

0.72

varargin

0.72

matlab

0.71

0.69

0.65

AutoField

0.63

hObject

0.61

Activations Density 1.821%

code snippets particularly with coordinate transformations or image processing functions

isempty

No Comments

No Known Activations