INDEX

Explanations

the word "ordinary"

oai_token-act-pair · gemini-2.0-flash

ordinary

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

 itſelf

-2.27

 myſelf

-2.25

Efq

-2.17

 themſelves

-2.05

 Jefus

-2.00

 houſe

-1.97

 purpoſe

-1.96

 Monfieur

-1.95

ſelves

-1.93

 Majefty

-1.91

POSITIVE LOGITS

1.06

1.03

1.00

0.99

0.98

0.93

0.92

0.91

0.90

Activations Density 1.286%

the word "ordinary"

ordinary

No Comments

No Known Activations