INDEX

Explanations

the word "la" and other Spanish words, sometimes activating for "var" and "simple".

oai_token-act-pair · gemini-2.0-flash

la

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

la

-2.64

la

-1.63

La

-1.48

La

-1.45

Lac

-1.08

LA

-1.07

lap

-1.01

Lac

-0.98

LA

-0.97

Lap

-0.95

POSITIVE LOGITS

the

0.66

 cuadro

0.52

 bénéfices

0.51

 myce

0.51

enthe

0.51

 producteurs

0.50

 skak

0.50

The

0.50

 Públicas

0.50

 håll

0.49

Activations Density 0.045%

the word "la" and other Spanish words, sometimes activating for "var" and "simple".

la

No Comments

No Known Activations