INDEX

Explanations

words relating to measurements or intensity

oai_token-act-pair · gemini-2.0-flash

high

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

 high

-1.44

low

-1.41

high

-1.22

High

-1.19

 High

-1.13

Low

-1.10

Low

-1.09

 higher

-1.09

low

-1.05

HIGH

-1.03

POSITIVE LOGITS

 <<<<<<<<<<<<<<

0.57

side

0.48

\"");

0.46

 /\.(

0.46

first

0.45

entuh

0.45

 Erster

0.44

 catalyzed

0.44

evos

0.44

esez

0.43

Activations Density 4.796%

words relating to measurements or intensity

high

No Comments

No Known Activations