INDEX

Explanations

code snippets with conditional logic, array brackets, and functions

oai_token-act-pair · gemini-2.0-flash

code snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

Efq

-1.02

 Theſe

-1.02

 Monfieur

-0.96

 myſelf

-0.91

 Jefus

-0.86

 doubtnut

-0.84

 ModelExpression

-0.84

 تكبرها

-0.83

таратура

-0.81

^(@)

-0.80

POSITIVE LOGITS

 "..\..\..\

0.59

IBOutlet

0.49

0.47

 GeoNames

0.42

.*;

0.40

<bos>

0.38

 "..\..\

0.38

 Kines

0.36

&#

0.35

0.34

Activations Density 1.718%

code snippets with conditional logic, array brackets, and functions

code snippets

No Comments

No Known Activations