INDEX

Explanations

units of measure

oai_token-act-pair · gemini-2.0-flash

degrees

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

-0.98

<eos>

-0.75

-0.71

↵

-0.70

-0.69

-0.66

Be

-0.63

-0.62

-0.61

-0.60

POSITIVE LOGITS

Efq

1.45

 Theſe

1.42

 itſelf

1.41

 myſelf

1.41

 Monfieur

1.35

 raiſ

1.34

 Reſ

1.27

 himſelf

1.24

 Majefty

1.23

ſelf

1.22

Activations Density 1.866%

units of measure

degrees

No Comments

No Known Activations