INDEX

Explanations

phrases related to the education level of students

oai_token-act-pair · gemini-2.0-flash

school grades

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

 high

-1.31

high

-1.25

High

-1.16

 High

-1.04

 HIGH

-0.96

HIGH

-0.94

 alta

-0.71

高

-0.71

Высо

-0.71

 hoog

-0.71

POSITIVE LOGITS

uração

0.45

UseVisualStyle

0.44

ínu

0.44

abestanden

0.42

 Byers

0.42

 désolés

0.42

 nguồn

0.41

ontent

0.41

ņu

0.41

 hmot

0.40

Activations Density 0.815%

phrases related to the education level of students

school grades

No Comments

No Known Activations