INDEX

Explanations

the word "hard" or a compound adjective starting with 'hard'

oai_token-act-pair · gemini-2.0-flash

hard

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

 JADX

-0.48

PBT

-0.48

MigrationBuilder

-0.47

例文帳に追加

-0.47

 مرئيه

-0.46

ngths

-0.45

ารถ

-0.45

 XCTest

-0.45

tagHelperRunner

-0.45

/*++

-0.44

POSITIVE LOGITS

 ModelExpression

0.68

bewerken

0.59

 SwitchCompat

0.59

/>";

0.57

 becauſe

0.57

 الرياضيه

0.57

 Theſe

0.57

urbs

0.54

ArgumentParser

0.54

bootstrapcdn

0.53

Activations Density 6.763%

the word "hard" or a compound adjective starting with 'hard'

hard

No Comments

No Known Activations