INDEX

Explanations

indented text

oai_token-act-pair · gemini-2.0-flash

legal, historical, procedural contexts

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

-4.13

 myſelf

-4.03

 Monfieur

-3.94

Efq

-3.84

 ―――――

-3.81

 Anſ

-3.78

 Majefty

-3.77

 purpoſe

-3.72

 iſt

-3.70

 Jefus

-3.69

POSITIVE LOGITS

2.81

↵↵

2.70

2.34

↵

2.33

2.06

2.02

The

1.97

1.95

1.94

1.92

Activations Density 0.313%

indented text

legal, historical, procedural contexts

No Comments

No Known Activations