INDEX

Explanations

auxiliary verbs and related words

oai_token-act-pair · gemini-2.0-flash

to

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 purpoſe

-1.01

 Houſe

-0.97

 becauſe

-0.96

Efq

-0.96

 myſelf

-0.93

 fubject

-0.91

 houſe

-0.91

 Theſe

-0.91

 Majefty

-0.90

 pleaſure

-0.90

POSITIVE LOGITS

ParallelGroup

0.54

win

0.50

 master

0.44

上

0.44

uz

0.43

 break

0.41

TabIndex

0.40

win

0.40

lay

0.40

Activations Density 2.576%

auxiliary verbs and related words

to

No Comments

No Known Activations