INDEX

Explanations

German language and grammar constructs

oai_token-act-pair · gemini-2.0-flash

foreign language

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Efq

-0.93

 Monfieur

-0.92

 Jefus

-0.83

 myſelf

-0.82

 purpoſe

-0.82

 itſelf

-0.82

はじめに

-0.79

 pleaſure

-0.77

 StatefulWidget

-0.76

 themſelves

-0.76

POSITIVE LOGITS

CTX

0.47

ArgsConstructor

0.47

Шаг

0.46

INCREF

0.46

Vapor

0.45

ArrayList

0.45

ramenta

0.44

 doors

0.43

consulté

0.43

Spacer

0.43

Activations Density 0.217%

German language and grammar constructs

foreign language

No Comments

No Known Activations