INDEX

Explanations

words related to education, training, faith and research

oai_token-act-pair · gemini-2.0-flash

learning/instruction

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 lessons

-1.18

lessons

-1.14

 lesson

-1.12

 Lessons

-1.11

Lessons

-1.03

 feedback

-0.96

 Lesson

-0.96

 LESSON

-0.90

 Feedback

-0.89

lesson

-0.89

POSITIVE LOGITS

 onCreateView

0.72

eclampsia

0.47

 mẽ

0.46

Lleg

0.45

 tanım

0.44

antMatchers

0.43

bmatrix

0.42

으며

0.40

degard

0.40

 maquina

0.40

Activations Density 10.024%

words related to education, training, faith and research

learning/instruction

No Known Activations